State evaluation method and system for invasive brain-computer interface system and medium

Abstract

The invention provides a state evaluation method and system for an invasive brain-computer interface system and a medium. The method comprises the following steps: randomly generating a test sequence, wherein the test sequence comprises a plurality of stimulation current intensity values; each stimulation current intensity value is sequentially sent to the extracorporeal machine, a body surface artifact signal is synchronously obtained, and when the extracorporeal machine receives the stimulation current intensity value every time, a corresponding stimulation instruction is generated and sent to the implant so as to control the implant to apply electrical stimulation according to the stimulation current intensity value; based on the body surface artifact signal corresponding to each stimulation current intensity value, a state evaluation result of the invasive brain-computer interface system is generated, and the state evaluation result comprises at least one of signal validity, a signal amplitude abnormal condition and a waveform distortion condition. The method objectively and accurately evaluates the working state of the invasive brain-computer interface system.

Description

Technical Field

[0001] This invention relates to the field of invasive brain-computer interface system technology, and more specifically to a method, system and medium for state assessment of invasive brain-computer interface systems. Background Technology

[0002] Invasive brain-computer interface (BCI) systems directly record neural electrical activity or apply electrical stimulation by implanting an electrode array within the nervous system to restore or enhance damaged neural function. Their normal operation relies on stable and reliable wireless (or percutaneous wired) data and energy transmission between an external processor (external unit) and the internal implant. Upon receiving coded control commands, the implant applies precise electrical pulses to the target neural tissue via its electrode array.

[0003] Currently, the assessment of the operational status of invasive brain-computer interface systems mainly relies on subjective feedback. Subjective assessment depends on the patient's active feedback, making it difficult to directly verify whether the implant accurately executed each stimulus command. This leads to difficulties in distinguishing whether abnormal assessment results are caused by "insufficient neural response" or "the implant failing to execute commands correctly," reducing the efficiency of problem localization.

[0004] In view of this, the present invention is hereby proposed. Summary of the Invention

[0005] The present invention is proposed in view of the above-mentioned problems. According to one aspect of the present invention, a method for state assessment of an invasive brain-computer interface system is provided, the invasive brain-computer interface system comprising an external unit and an implant; the method comprising: A test sequence is randomly generated, and the test sequence includes multiple stimulation current intensity values; Each of the stimulation current intensity values ​​is sequentially sent to the external device, and the artifact signal on the body surface is acquired simultaneously. Each time the external device receives the stimulation current intensity value, it generates a corresponding stimulation command and sends it to the implant to control the implant to apply electrical stimulation according to the stimulation current intensity value. Based on the surface artifact signal corresponding to each of the stimulation current intensity values, a state assessment result of the invasive brain-computer interface system is generated, and the state assessment result includes at least one of signal validity, abnormal signal amplitude, and waveform distortion.

[0006] For example, for each of the stimulation current intensity values, the surface artifact signal corresponding to the stimulation current intensity value is determined based on the surface artifact signal acquired within a first preset time period after the stimulation current intensity value is emitted. The process of generating a state assessment result for the invasive brain-computer interface system based on the surface artifact signal corresponding to each of the stimulation current intensity values ​​includes: Determine whether the artifact signal on the body surface corresponding to each of the stimulation current intensity values ​​is a valid signal; The validity of the signal is represented by at least one of the following data: the total number of valid signals, the total number of invalid signals, and the bit error rate, wherein the total number of invalid signals is the difference between the total number of signals and the total number of valid signals, and the bit error rate is the ratio of the total number of invalid signals to the total number of signals.

[0007] For example, determining whether the surface artifact signal corresponding to each of the stimulation current intensity values ​​is a valid signal includes: For any of the stimulation current intensity values ​​corresponding to the surface artifact signal, determine whether the peak amplitude of the surface artifact signal is greater than the weighting value of the baseline noise; The surface artifact signal is determined to be a valid signal at least when the peak amplitude of the signal is greater than the weighting value of the baseline noise.

[0008] For example, generating the state assessment result of the invasive brain-computer interface system based on the surface artifact signal corresponding to each of the stimulation current intensity values ​​includes: For any of the aforementioned stimulation current intensity values, the actual peak-to-peak value of the surface artifact signal is determined when the surface artifact signal is a valid signal. Determine the expected peak-to-peak value corresponding to the intensity of the stimulation current; The amplitude deviation is determined based on the actual peak-to-peak value and the expected peak-to-peak value. When the amplitude deviation is greater than the deviation threshold, the amplitude of the artifact signal on the body surface is determined to be abnormal. The abnormal signal amplitude is represented by at least one of the following data: the number of amplitude abnormality commands and the average amplitude deviation, wherein the number of amplitude abnormality commands is the total number of stimulation current intensity values ​​corresponding to the abnormal amplitude of the surface artifact signal, and the average amplitude deviation is the mean of the amplitude deviation corresponding to each valid signal.

[0009] Exemplarily, the method further includes: Each stimulation current intensity value in the calibration sequence is sent to the external machine in sequence, and the artifact signal on the body surface is acquired simultaneously. The calibration sequence is obtained by the following method: starting with a preset minimum stimulation current, the stimulation current intensity value is increased step by step according to a preset step size until the preset maximum stimulation current is reached. Determine the calibration peak-to-peak value of the surface artifact signal corresponding to each stimulus current intensity value in the calibration sequence; Based on each stimulation current intensity value in the calibration sequence and its corresponding calibration peak value, the relationship between the stimulation current intensity value and the calibration peak value is determined to obtain a preset fitting relationship; The step of determining the expected peak-to-peak value corresponding to the stimulation current intensity value includes: substituting the stimulation current intensity value into the preset fitting relationship to obtain the expected peak-to-peak value.

[0010] For example, generating the state assessment result of the invasive brain-computer interface system based on the surface artifact signal corresponding to each of the stimulation current intensity values ​​includes: For any of the aforementioned stimulation current intensity values, when the surface artifact signal is a valid signal, it is determined whether the similarity between the surface artifact signal and the baseline template corresponding to the stimulation current intensity value is less than the similarity threshold. When the similarity is less than the similarity threshold, the waveform of the artifact signal on the body surface is determined to be distorted. The total number of artifact signals on the body surface that cause waveform distortion is counted to obtain the waveform distortion count; The waveform distortion condition includes the number of waveform distortions and at least one of the following: average waveform correlation coefficient and waveform distortion rate; wherein the average waveform correlation coefficient is the mean of the similarity corresponding to each valid signal.

[0011] For example, the first preset time period is determined in the following way: The preset stimulation current intensity value is sent to the external machine, and the artifact signal on the body surface is acquired simultaneously to obtain the waveform template. Based on the waveform template, the first preset time period is determined, wherein the start time of the first preset time period is the time difference between the time when the preset stimulation current intensity value is emitted and the time when the signal value in the waveform template begins to deviate from the baseline, and the end time of the first preset time period is the time difference between the time when the signal value in the waveform template completely returns to the baseline noise level and the time when the signal value in the waveform template begins to deviate from the baseline.

[0012] For example, before generating the state assessment result of the invasive brain-computer interface system based on the surface artifact signal corresponding to each of the stimulation current intensity values, the method further includes: The surface artifact signal obtained from each transmission of the stimulation current intensity value is filtered using a high-pass filter. or, Baseline signals are continuously acquired during a second preset time period before the stimulation current intensity value is sent, and the signal mean is calculated; For each time the stimulation current intensity value is sent, the surface artifact signal obtained is subtracted from the signal mean point by point to achieve baseline correction.

[0013] According to another aspect of the present invention, a status assessment system for an invasive brain-computer interface system is provided, the invasive brain-computer interface system comprising an external unit and an implant; the status assessment system comprising a host computer and a signal acquisition device; the signal acquisition device being used to acquire surface artifact signals; the host computer being connected to the external unit and the signal acquisition device respectively; the host computer being used to implement the above-described method.

[0014] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores a computer program / instructions that, when executed by a processor, implement the method described above.

[0015] Compared with the prior art, the present invention has at least the following technical effects: 1. By randomly generating test sequences containing multiple stimulation current intensity values, it is possible to simulate diverse system operation stimulation scenarios, avoid the limitations of evaluation results under single test conditions, and improve the comprehensiveness and objectivity of the evaluation; 2. By simultaneously acquiring surface artifact signals while sending each stimulation current intensity value to an external device, and generating a status assessment result based on the surface artifact signals corresponding to each stimulation current intensity value, which covers at least one of the following: signal validity, abnormal signal amplitude, and waveform distortion, on the one hand, it can completely eliminate the dependence on subjective feedback from patients, achieve objective assessment, and improve the accuracy of results; on the other hand, this method of continuous random sequence testing can detect some sporadic and difficult-to-reproduce intermittent missing codes or signal distortions, which are "ghost faults" that are almost impossible to detect by traditional methods. 3. This method only requires attaching electrodes to the body surface to collect artifact signals. No additional invasive operations are required. It is non-invasive, radiation-free, simple to operate, and easy to implement in clinical practice. It can be operated by professionals in outpatient clinics, operating rooms, or home environments. 4. This scheme can evaluate the working status of each stimulation current intensity value using a one-to-one correspondence of each artifact signal on the body surface. The evaluation results, such as signal validity, abnormal signal amplitude, and waveform distortion, can provide medical personnel with accurate and intuitive references, allowing them to intuitively "see" the output of the implant. This facilitates the precise identification of specific problem sources (external machine coding problems, wireless transmission / coupling problems, implant circuit failures, etc.) and enables rapid stratified localization of faults. 5. The status assessment results obtained by this scheme can also be quantitatively stored as a long-term "health record" of the implant, which is convenient for tracking the performance degradation trend and realizing predictive maintenance.

[0016] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0017] The above and other objects, features, and advantages of the present invention will become more apparent from the more detailed description of the embodiments of the invention in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same parts or steps.

[0018] Figure 1 A schematic flowchart of a state assessment method according to an embodiment of the present invention is shown; Figure 2 A schematic diagram of a state assessment system according to an embodiment of the present invention is shown.

[0019] Figure 2 In the middle, 210 is the cochlear implant sound processor; 220 is the host computer; and 230 is the signal acquisition device. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the present invention more apparent, exemplary embodiments according to the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are merely a part of the embodiments of the present invention, and not all of the embodiments of the present invention. It should be understood that the present invention is not limited to the exemplary embodiments described herein. Based on the embodiments of the present invention described herein, all other embodiments obtained by those skilled in the art without inventive effort should fall within the protection scope of the present invention.

[0021] In this article, invasive brain-computer interface systems include, but are not limited to, spinal cord stimulators, deep brain stimulators, visual cortex stimulators, and cochlear implants. As mentioned above, current assessments of the operational status of invasive brain-computer interface systems heavily rely on subjective feedback. For example, for cochlear implants, it depends on what the patient "hears"; for deep brain stimulation (DBS) treatment of Parkinson's disease, it depends on whether the patient's "tremor has lessened"; and for spinal cord stimulation (SCS) analgesia, it depends on the patient's "pain score." This is not only limited by the patient's cognitive and expressive abilities but also cannot distinguish between "insufficient neural response" and "the implant not correctly executing instructions." Some related technologies consider using methods such as impedance telemetry, neural pathway function assessment, and implant-based diagnostics to test the system. However, impedance telemetry can only assess the electrical characteristics of a single electrode-tissue interface (such as open circuit or short circuit) and cannot reflect whether the complete waveform, amplitude, or timing of the stimulation pulse is correct. Telemetry techniques for assessing neural pathway function, such as electrically evoked auditory brainstem response (EABR) and electrically evoked compound action potential (ECAP), are used to evaluate the integrity of neural pathways from the auditory nerve to the central nervous system. However, neural responses are influenced by various physiological factors, including neural excitability, anesthesia status, and individual differences in neuroanatomy. Their presence or amplitude cannot be directly equated to the integrity of the stimulus output. While implant-based diagnostics can perform some self-checking, they can only report limited internal parameters (such as voltage) and cannot independently verify the actual stimulus signal output to the electrode tip. In short, neither subjective nor objective testing methods can directly verify whether the implant accurately executed every stimulus command. When patients (especially those unable to communicate) report auditory abnormalities, current technologies struggle to distinguish between "insufficient neural response" and "the implant not correctly executing commands," affecting the efficiency of problem localization. In view of this, the present invention provides a method, system, and medium for state assessment of invasive brain-computer interface systems. This method can intuitively monitor the execution of stimulation commands corresponding to each stimulation current intensity value by the implant, achieving an objective quantitative assessment of the invasive brain-computer interface system. This allows clinicians to easily distinguish whether the problem is caused by "insufficient neural response" or "the implant not correctly executing commands" when abnormalities occur, improving the efficiency of problem localization. The method, system, and medium are described in detail below.

[0022] According to one aspect of the present invention, a method for state assessment of an invasive brain-computer interface system is provided. The invasive brain-computer interface system includes an external unit and an implant.

[0023] Figure 1 A schematic flowchart illustrating a state assessment method according to an embodiment of the present invention is shown. Figure 1 As shown, the method may include the following steps S110, S120 and S130.

[0024] In step S110, a test sequence is randomly generated, which includes multiple stimulation current intensity values.

[0025] The stimulation current intensity value can be referred to as the CL value. In this example, multiple CL values ​​can be randomly generated within the operating range of the invasive brain-computer interface system to form a test sequence. The operating range of the invasive brain-computer interface system can be determined empirically. The number of CL values ​​in the test sequence can be selected as needed. In one embodiment, the test sequence may include 200 random CL values, in which case the test sequence can be represented as: .

[0026] In step S120, each stimulation current intensity value is sent to the external machine in sequence, and the artifact signal on the body surface is acquired simultaneously; wherein, each time the external machine receives a stimulation current intensity value, it generates a corresponding stimulation command and sends it to the implant to control the implant to apply electrical stimulation according to the stimulation current intensity value.

[0027] After obtaining the test sequence, each stimulation current intensity value can be sent to the external device sequentially according to the order in the test sequence. Each time the external device receives a stimulation current intensity value, it can convert it into a corresponding stimulation command and transmit it to the implant. When the implant receives the stimulation command, it can apply precise electrical pulse stimulation to the target nerve tissue through its electrode array according to the stimulation command.

[0028] When electrical stimulation is applied to the target neural tissue, the stimulation is conducted within the body's volumetric conductors and transmitted to the skin surface, generating a weak potential difference, known as a stimulation artifact. In this example, this stimulation artifact can be acquired in real time as a surface artifact signal while electrical stimulation is performed sequentially according to the stimulation sequence. This surface artifact signal can be acquired using a multi-channel, high-sampling-rate, high-resolution bioelectrical signal acquisition device. The device's input can be connected to multiple recording electrodes applied to the patient's skin (near the implantation area) for synchronous, non-invasive, and high-fidelity capture of the surface potential signal (i.e., the surface artifact signal) generated by the implant's electrical stimulation.

[0029] In this paper, the surface artifact signal is a signal curve composed of multiple signal values ​​acquired continuously over a period of time. The acquisition frequency of the surface artifact signal can be selected as needed. In some embodiments, the acquisition frequency of the surface artifact signal can be 5 to 10 times the sampling rate of the highest frequency of the signal. According to the Nyquist-Shannon sampling theorem, to reconstruct an analog signal without distortion, the sampling frequency must be greater than twice the highest frequency component of the signal. In this embodiment, a sampling rate of 5 to 10 times the highest frequency of the signal is selected to capture signal details (such as the rising edge of the pulse) more accurately. For example, for a stimulus artifact with a pulse width of 25 μs, choosing a sampling rate of 100 kHz or higher is a reasonable and safe starting point.

[0030] In step S130, based on the surface artifact signal corresponding to each stimulation current intensity value, a state assessment result of the invasive brain-computer interface system is generated. The state assessment result includes at least one of signal validity, signal amplitude abnormality, and waveform distortion. This state assessment result can be output in the form of a report text.

[0031] The above solution is for invasive brain-computer interface systems with a single electrode / channel. In some scenarios, when the invasive brain-computer interface system has multiple channels / electrodes, each channel / electrode of the implant can be tested by repeating steps S110, S120, and S130, and the final evaluation result can be generated based on the status evaluation results of each channel. This will not be elaborated further.

[0032] The inventors discovered that artifacts are instantaneous potential fields generated when a stimulating current flows through tissue. These artifacts are the most direct and objective physical evidence of implant function; their existence proves that stimulation has been output, and their shape and amplitude encode the parameter information of the stimulation. Therefore, in this example, the surface artifact signal corresponding to each stimulation current intensity value is considered as an "information carrier" for assessing the implant's functional status. Specifically, the validity of a single signal can be determined based on the presence or absence of the surface artifact signal and its signal characteristics. When the signal is invalid, the stimulation current intensity value has a missing code. By statistically analyzing the validity of surface artifact signals corresponding to different stimulation current intensity values, the signal validity result reflecting the missing code status of the invasive brain-computer interface system can be obtained. The statistical results of amplitude abnormalities can be obtained by statistically analyzing the amplitude abnormalities of each surface artifact signal, i.e., the signal amplitude abnormality status. The waveform distortion status can be obtained by statistically analyzing the distortion degree of each surface artifact signal, which will not be elaborated upon. This information can intuitively reflect the completeness of the stimulation output, thereby directly verifying whether the implant accurately executes the stimulation command corresponding to each stimulation current intensity value.

[0033] The above-mentioned scheme can simulate diverse system operation stimulation scenarios by randomly generating test sequences containing multiple stimulation current intensity values, avoiding the limitations of evaluation results under single test conditions and improving the comprehensiveness and objectivity of the evaluation. By simultaneously acquiring surface artifact signals while sending each stimulation current intensity value to the external machine, and generating a status evaluation result covering at least one of signal validity, abnormal signal amplitude, and waveform distortion based on the surface artifact signals corresponding to each stimulation current intensity value, on the one hand, it can completely eliminate the dependence on subjective feedback from patients, achieve objective evaluation, and improve the accuracy of results; on the other hand, this method of continuous random sequence testing can discover some sporadic and difficult-to-reproduce intermittent missing codes or signal distortions, which are "ghost faults" that are almost impossible to detect by traditional methods.

[0034] In addition, this method only requires attaching electrodes to the body surface to collect artifact signals, without any additional invasive operations. It is non-invasive, radiation-free, simple to operate, and easy to implement clinically. It can be operated by professionals in outpatient clinics, operating rooms, or home environments.

[0035] In addition, this scheme can evaluate the working status of each stimulation current intensity value using a one-to-one correspondence of each artifact signal on the body surface. The evaluation results, such as signal validity, abnormal signal amplitude, and waveform distortion, can provide medical personnel with accurate and intuitive references, allowing them to intuitively "see" the output of the implant. This facilitates the medical personnel to accurately distinguish the specific source of the problem (external machine coding problem, wireless transmission / coupling problem, implant circuit failure, etc.) and facilitates rapid stratified localization of the fault.

[0036] Furthermore, this scheme triggers each stimulation current intensity value only once. By triggering multiple stimulation current intensity values ​​sequentially, it is possible to capture intermittent, randomly occurring missed codes or distortions, ensuring the randomness and unpredictability of the test and improving its rigor. On the other hand, it can improve testing efficiency and facilitate rapid test completion (assuming 20 different CL values ​​are tested, each repeated 10 times, it would require 200 stimulations. Even at a rate of 10 stimulations per second, it would take 20 seconds. A single test (one measurement per CL value) only takes 2 seconds), making it particularly suitable for patients who cannot remain still for extended periods (such as infants).

[0037] The status assessment results obtained by this scheme can also be quantitatively stored as a long-term "health record" for the implant, which facilitates tracking performance degradation trends and enabling predictive maintenance.

[0038] In summary, the above-mentioned status assessment method is simple to operate and easy to use. It can directly verify whether the implant accurately executes the stimulation command corresponding to each stimulation current intensity value, thereby objectively and accurately assessing the working status of the invasive brain-computer interface system. It is especially suitable for the functional assessment of invasive brain-computer interface systems in infants, aphasic patients, and patients with consciousness disorders.

[0039] In the scheme described in this paper, for each stimulation current intensity value, the corresponding surface artifact signal is determined based on the surface artifact signal acquired within a first preset time period after the transmission of that stimulation current intensity value. It can be understood that the surface artifact signal appears within a very short time window (e.g., 0.1 ms to 2 ms) after the external control unit sends a stimulation command to the implant, i.e., the first preset time period. This first preset time period can be determined empirically or obtained through actual measurements on the current patient.

[0040] In some embodiments, the first preset time period is determined by: sending a preset stimulation current intensity value to an external device and simultaneously acquiring surface artifact signals to obtain a waveform template; determining the first preset time period based on the waveform template, wherein the start time of the first preset time period is the time difference between the time when the preset stimulation current intensity value is emitted and the time when the signal value in the waveform template begins to deviate from the baseline, and the end time of the first preset time period is the time difference between the time when the signal value in the waveform template completely returns to the baseline noise level and the time when the signal value in the waveform template begins to deviate from the baseline.

[0041] In this embodiment, a known, properly functioning parameter (e.g., a high CL value to ensure obvious artifacts) can be pre-selected as the preset stimulation current intensity. After the preset stimulation current intensity is emitted, the signal is continuously acquired in real-time to obtain a waveform template composed of multiple signal values. This standard template can then be analyzed. The time from when the signal begins to deviate from the baseline (typically within 0.1-2 milliseconds after the stimulation command is issued) to when the signal completely returns to the baseline noise level is determined. Based on the above measurements, a fixed analysis time window can be defined. T start , T end ],in, T start The moment the stimulus command is issued T trigger This is followed by a fixed delay, for example, 0.1 ms. This delay is the physiological time required for the signal to travel from the stimulation point to the recording electrode. T end = T start +Δ t , where Δ tThe duration of the artifact's main energy, measured from the template, is related to the actual stimulus pulse width and depends on the stimulus parameters and recording location. This time window is the first preset time period. Within this window, the artifact signal generated by that stimulus can be found.

[0042] The above scheme relies on the waveform template of the actual acquired surface artifact signal as the basis for definition, avoiding the problem that the fixed time period setting may not match the actual stimulus response process. This makes the definition of the first preset time period more in line with the real signal change pattern and helps to adapt to the differences of different individuals, thereby obtaining surface artifact signals more accurately.

[0043] Research has revealed that the initial surface artifact signals acquired each time contain baseline drift. To improve signal quality, preprocessing can be performed on the surface artifact signals after each acquisition. This preprocessing includes, but is not limited to, baseline correction and digital filtering. Several examples illustrate some of these preprocessing methods in detail below.

[0044] In some embodiments, before generating the state assessment result of the invasive brain-computer interface system based on the surface artifact signal corresponding to each stimulation current intensity value, the method further includes: filtering the surface artifact signal obtained from each transmission of stimulation current intensity value using a high-pass filter.

[0045] As mentioned above, the directly acquired surface artifact signal includes baseline drift. This is a low-frequency interference that may originate from changes in electrode contact impedance, slow body movement of the subject, or slowly changing background neural electrical activity. Baseline drift is typically concentrated in the very low frequency range (e.g., below 0.5 Hz). In this embodiment, we consider effectively removing it through digital high-pass filtering (e.g., with a cutoff frequency of 0.1–1 Hz). This can further improve signal quality.

[0046] Of course, besides high-pass filtering, baseline drift can also be eliminated directly through baseline correction. In some embodiments, before generating the state assessment result of the invasive brain-computer interface system based on the surface artifact signal corresponding to each stimulus current intensity value, the method further includes: continuously acquiring baseline signals and calculating the signal mean during a second preset time period before sending the stimulus current intensity value; for each surface artifact signal obtained by sending a stimulus current intensity value, subtracting the signal mean point by point from the surface artifact signal to achieve baseline correction. In this embodiment, the average signal is calculated during a quiet period (e.g., -5 ms to -1 ms) before the stimulus is emitted. Then subtract this average value from the entire signal segment. The result after subtracting the average value is... It can be represented as: Compared to directly using a high-pass filter for filtering, this method offers more precise drift suppression, better reflects real-world scenarios, and features a simpler algorithm with lower computational cost, helping to reduce the method's operating costs. It also better aligns with the processing characteristics and engineering requirements of short-term neural response signals in invasive brain-computer interface systems.

[0047] Furthermore, bandpass filtering can be used for signal preprocessing. For example, a suitable bandpass filter can be designed based on the known frequency characteristics of the stimulus artifact, which can preserve the main energy of the artifact while suppressing out-of-band noise.

[0048] For example, step S130, generating a state assessment result of the invasive brain-computer interface system based on the surface artifact signal corresponding to each stimulation current intensity value, includes the following steps: determining whether the surface artifact signal corresponding to each stimulation current intensity value is a valid signal; wherein, the signal validity is represented by at least one of the following data: the total number of valid signals, the total number of invalid signals, and the bit error rate, wherein the total number of invalid signals is the difference between the total number of signals and the total number of valid signals, and the bit error rate is the ratio of the total number of invalid signals to the total number of signals.

[0049] In this example, the approach considers determining whether the surface artifact signal corresponding to each stimulation current intensity value is a valid signal. For example, the signal-to-noise ratio (SNR) of the surface artifact signal can be calculated. If the SNR is greater than or equal to a threshold (selected based on actual needs or determined empirically), the surface artifact signal is considered valid. Otherwise, the surface artifact signal is determined to be invalid. Alternatively, the validity of the surface artifact signal can be determined based on its characteristics (e.g., waveform, pulse peak direction). If the signal is invalid, it indicates a code leak at the current stimulation current intensity value, suggesting a potential problem with the implant.

[0050] After analyzing each signal to determine its validity, the total number of valid signals and invalid signals can be obtained. The code leakage rate can then be calculated based on the ratio of the total number of invalid signals to the total number of signals (which is the same as the number of stimulation current intensity values). This information reflects the code leakage status of the implant in the current system. Furthermore, signal validity can also include the stimulation current intensity value corresponding to each invalid signal, allowing medical personnel to intuitively identify the scenario in which code leakage occurs, facilitating rapid troubleshooting and maintenance.

[0051] The above-described scheme clearly distinguishes the signal validity of surface artifact signals corresponding to each stimulation current intensity value through steps, which can directly locate the quality differences in signal acquisition under different current intensities and whether there are missing codes, providing a direct basis for subsequent optimization of stimulation parameters. On the other hand, by using at least one of the three core data types—total number of valid signals, total number of invalid signals, and bit error rate—as evaluation indicators, it can not only intuitively reflect the effective scale of signal acquisition from an absolute quantity perspective, but also accurately measure the error level in the signal transmission and acquisition process from a relative proportion perspective through the bit error rate. This allows for the comprehensive and objective generation of system status evaluation results, effectively supporting the judgment of the stability, reliability, and adaptability of signal acquisition in invasive brain-computer interface systems, and providing scientific data support for system performance optimization, fault diagnosis, and parameter adjustment in clinical applications.

[0052] For example, determining whether the surface artifact signal corresponding to each stimulation current intensity value is a valid signal includes: for any surface artifact signal corresponding to a stimulation current intensity value, determining whether the peak amplitude of the surface artifact signal is greater than the weighted value of the baseline noise; at least when the peak amplitude of the surface artifact signal is greater than the weighted value of the baseline noise, determining that the surface artifact signal is a valid signal.

[0053] In this example scheme, the peak amplitude of the signal must be significantly greater than the baseline noise before stimulation, i.e., it must satisfy... ,in This represents the standard deviation of noise (i.e., baseline noise). The weighting value is usually between 3 and 5.

[0054] In some embodiments, when the peak amplitude of the surface artifact signal is greater than the weighting value of the baseline noise, it can be further determined whether the surface artifact signal has the expected basic morphology. This basic morphology is determined according to the invasive brain-computer interface system, and may be, for example, biphasic polarity, etc., which is not limited herein. When the surface artifact signal has the expected basic morphology, the surface artifact signal is determined to be valid.

[0055] The above scheme can more accurately determine signal validity, providing a high-quality data foundation for subsequent implant problem diagnosis based on the missing code situation reflected by validity.

[0056] For example, step S130, generating a state assessment result of the invasive brain-computer interface system based on the surface artifact signal corresponding to each stimulation current intensity value, may further include the following steps: for any surface artifact signal corresponding to a stimulation current intensity value, when the surface artifact signal is a valid signal, determining the actual peak-to-peak value of the surface artifact signal; determining the expected peak-to-peak value corresponding to the stimulation current intensity value; determining the amplitude deviation based on the actual peak-to-peak value and the expected peak-to-peak value; and determining that the amplitude of the surface artifact signal is abnormal when the amplitude deviation is greater than the deviation threshold. The abnormal amplitude condition is represented by at least one of the following data: the number of amplitude abnormal commands and the average amplitude deviation, where the number of amplitude abnormal commands is the total number of stimulation current intensity values ​​with abnormal amplitude corresponding to the surface artifact signal, and the average amplitude deviation is the average amplitude deviation corresponding to each valid signal. The abnormal amplitude condition may also include the stimulation current intensity value corresponding to each surface artifact signal with abnormal amplitude, which further facilitates fault diagnosis.

[0057] In this example, the scheme considers comparing the actual peak-to-peak value with the expected peak-to-peak value to determine whether the amplitude of the current surface artifact signal is abnormal. The actual peak-to-peak value is the difference between the maximum and minimum signal values ​​in the surface artifact signal, which can be expressed as: ; in, This represents the actual peak-to-peak value. This indicates artifact signals on the body surface.

[0058] In this example, based on the actual peak-to-peak value... Compared with the expected peak value Determine the amplitude deviation, which can be the ratio of the absolute value of the difference between the two values ​​to the expected peak-to-peak value. Specifically, it can be expressed as: If the ratio exceeds the deviation threshold (e.g., 5%), it indicates an amplitude abnormality at the current stimulation current intensity value.

[0059] By individually determining whether each surface artifact signal exhibits amplitude abnormalities, the number of amplitude abnormality commands can be statistically analyzed. Furthermore, the average amplitude deviation can be obtained by calculating the mean amplitude deviation corresponding to each valid surface artifact signal. These signal amplitude abnormalities can provide medical personnel with a reliable basis for determining the working status of the implant and whether it exhibits any malfunctions.

[0060] For example, the method further includes: sequentially sending each stimulation current intensity value in the calibration sequence to an external device and simultaneously acquiring surface artifact signals, wherein the calibration sequence is obtained by: starting with a preset minimum stimulation current, increasing the stimulation current intensity value step by step until a preset maximum stimulation current is reached; determining the calibration peak-to-peak value of the surface artifact signal corresponding to each stimulation current intensity value in the calibration sequence; determining the relationship between the stimulation current intensity value and the calibration peak-to-peak value based on each stimulation current intensity value in the calibration sequence and its corresponding calibration peak-to-peak value to obtain a preset fitting relationship; wherein calculating the expected peak-to-peak value corresponding to the stimulation current intensity value includes: substituting the stimulation current intensity value into the preset fitting relationship to obtain the expected peak-to-peak value.

[0061] The preset minimum stimulation current and preset maximum stimulation current can be determined according to the actual working conditions, and will not be elaborated here.

[0062] Let's take a cochlear implant as an example. A cochlear implant setup diagram (MAP) can be pre-entered. Then, according to the MAP parameters, the stimulation current can be increased incrementally in preset steps (e.g., 3) until the maximum comfort value is reached, with stable stimulation at least once at each CL value. Each CL value can be represented as: ,in, .

[0063] In some embodiments, the stimulus can be stably applied multiple times at each CL value, for example, 20 times. Then, the average of each stimulus is summed at the lock-time to obtain a stable, low-noise "averaged artifact waveform" at that CL value. Next, the peak-to-peak value of the average waveform is extracted. ; in: This represents the artifact detection window, which can be equivalent to the first preset time period.

[0064] For all tested CL values, fit the "CL-artifact amplitude standard response curve" for the electrode, and store the parameters and waveform template of the curve. The standard response curve (i.e., the preset fitting relationship) can be expressed as: ; in, Indicates the stimulation current level as The expected peak amplitude (µV) of skin surface irritation artifacts. Indicates the level of stimulation current (dimensionless integer). The coefficients are polynomials, determined by fitting calibration data using the least squares method.

[0065] Obtained during the calibration phase Data points The coefficients can then be determined by solving the following system of normal equations: .

[0066] During the inference phase, the current stimulation current intensity value can be directly substituted into the preset fitting relationship to determine the expected peak-to-peak value.

[0067] The above method can achieve personalized calibration for different individuals, obtain the preset fitting relationship for that individual more accurately, improve the accuracy of the predicted peak value, and thus more accurately determine whether the signal amplitude is abnormal.

[0068] In some embodiments, starting with a preset minimum stimulation current, the stimulation current intensity value is increased incrementally according to a preset step size until a preset maximum stimulation current is reached, including: for each stimulation current intensity value, repeatedly sending it to the external device a preset number of times, and obtaining the surface artifact signal obtained each time the stimulation current intensity value is sent; calculating the average value of the surface artifact signal obtained each time the stimulation current intensity value is sent, so as to obtain the surface artifact signal corresponding to the stimulation current intensity value.

[0069] The preset number of times can be selected as needed, for example, 20 times. In this embodiment, each stimulation current intensity value is repeatedly sent a preset number of times before the next stimulation current intensity value in the calibration sequence is sent. Taking a preset number of times of 20 times as an example, 20 sets of surface artifact signals can be obtained after each stimulation current intensity value is sent. Then, these 20 sets of surface artifact signals are superimposed and averaged to obtain the surface artifact signal corresponding to the stimulation current intensity value. This averaging process can be expressed as: ;in, This represents the surface artifact signal obtained after averaging. K Indicates the preset number of times.

[0070] During their research, the inventors discovered that the directly acquired surface artifact signals include random noise signals. This random noise is caused by random errors introduced by measuring instruments, environmental electromagnetic interference, etc. It is typically modeled as a zero-mean random process (e.g., Gaussian white noise), whose characteristics are independent and uncorrelated across different trials k. Considering that the calibration process requires an extremely high signal-to-noise ratio to establish a precise "ruler" for the calibration peak-to-peak values ​​and preset fitting relationships, in this example, the same stimulus current intensity value is repeated multiple times (e.g., 20 times). The recorded signals are then aligned temporally (using the stimulus emission time as the reference point) and averaged to suppress noise. Since the random noise has a zero mean and is uncorrelated between trials, the averaged noise power is reduced to 1 / 3 of its original value. K This significantly improves the signal-to-noise ratio, allowing for a more accurate determination of the preset fitting relationship.

[0071] It is important to note that in this scheme, random noise is only considered during the calibration process through averaging. In the actual testing process (steps S110, S120, and S130), each stimulus current intensity value is triggered only once. This is because the focus in actual testing is on "whether this stimulus is correct," not "what the average response of this CL value is." As long as the signal-to-noise ratio of a single signal is sufficient for validity detection (i.e., determining the presence or absence of a signal) and coarse feature extraction (calculating amplitude and correlation coefficient), a judgment can be made. A certain amount of noise is permissible as long as it does not affect the basic judgment of "presence / absence" and "similar / dissimilar." Moreover, removing random noise requires repeatedly sending the same stimulus current intensity value multiple times, which not only significantly prolongs the testing time but also affects the randomness of the test, making it difficult to capture intermittent, randomly occurring missed codes or distortions. Therefore, in actual testing, each stimulus current intensity value in the randomly generated test sequence only needs to be triggered once.

[0072] For example, based on the surface artifact signal corresponding to each stimulus current intensity value, a state assessment result of the invasive brain-computer interface system is generated, including: for any surface artifact signal corresponding to a stimulus current intensity value, if the surface artifact signal is a valid signal, determining whether the similarity between the surface artifact signal and the baseline template corresponding to the stimulus current intensity value is less than a similarity threshold; if the similarity is less than the similarity threshold, determining that the waveform of the surface artifact signal is distorted; counting the total number of waveform-distorted surface artifact signals to obtain the waveform distortion count; wherein, the waveform distortion status includes the waveform distortion count and at least one of the following: average waveform correlation coefficient, waveform distortion rate; wherein, the average waveform correlation coefficient is the mean of the similarity corresponding to each valid signal. The waveform distortion status may also include the stimulus current intensity value corresponding to each waveform-distorted surface artifact signal, which can further facilitate fault diagnosis.

[0073] In this paper, the baseline template is established in advance through an independent, high-confidence process, with the system pre-set to be fully functional, and serves as a fixed reference benchmark for all subsequent tests. The establishment timing is as follows: baseline calibration is performed immediately after the patient's postoperative recovery is stable and routine adjustments confirm the implant is functioning well. The acquisition method involves repeatedly sending dozens or even hundreds of stimuli with the same stimulation parameters (such as a specific electrode or a specific CL value), simultaneously acquiring the responses, and preprocessing and time-locked averaging these multiple responses. In a specific embodiment, the first... Baseline template for each CL value This can be achieved through the following steps: First, control the external machine, using the electrode, the... Each CL value is sent with K identical stimuli. Each stimulus is synchronized via hardware, triggering a data acquisition card to collect a fixed-duration segment of surface signal. The signal acquired during the k-th stimulus for the i-th CL value is... It can be represented as: ; in, Indicates the baseline template. Indicates random noise. This indicates baseline drift.

[0074] Next, for each acquired signal Preprocessing is performed: baseline correction and bandpass filtering are performed to obtain... Based on the trigger time of each stimulus, all segment signal Strictly align in time. Finally, the aligned... The average artifact waveform at that CL value is obtained by averaging the segment signal point by point, i.e., the baseline template: .

[0075] When calculating similarity, a sequence of signal values ​​from the signal curve of the surface artifact signal and a sequence of signal values ​​from the baseline template can be used. In some embodiments, before comparing similarity, it can be pre-determined whether the lengths of the surface artifact signal and the corresponding baseline template are the same. Then, the signal values ​​of the surface artifact signal and the baseline template are standardized to eliminate the influence of DC bias.

[0076] For surface artifact signals, the standardization process can be expressed by the following formula: .

[0077] For a baseline template, the normalization process can be expressed by the following formula: .

[0078] After standardization, the Pearson correlation coefficient between the two can be calculated as the similarity using the following formula: .

[0079] Alternatively, the Pearson correlation coefficient between the two can be calculated using the sample standard deviation: .

[0080] If the similarity is below a similarity threshold (e.g., 0.9), the waveform of the artifact signal on the current body surface can be considered distorted. This may indicate a fault in the implant's output drive circuit, a drastic change in coupling efficiency, or other issues.

[0081] It is understood that in the embodiment that uses the characteristics of the surface artifact signal and compares the surface artifact signal with the artifact signal curve template under the predetermined stimulation current intensity value to determine the validity of the signal, the similarity calculated in the above steps can be directly reused when judging whether the waveform is distorted, without going into details.

[0082] After determining whether each artifact signal on the body surface is distorted, the number of waveform distortions can be counted, and the waveform distortion rate (the ratio of the number of waveform distortions to the number of valid signals) and the average waveform correlation coefficient can be calculated based on the number of waveform distortions. This will not be elaborated further.

[0083] The above scheme can accurately determine whether the artifact signal on each body surface is distorted, and generate waveform distortion results based on the distortion status. This can provide a reliable basis for evaluating the working status and functional status of the implant in subsequent processes.

[0084] According to another aspect of the present invention, a status assessment system for an invasive brain-computer interface system is provided. The invasive brain-computer interface system includes an external machine and an implant. The status assessment system includes a host computer and a signal acquisition device. The signal acquisition device is used to acquire artifact signals from the body surface. The host computer is connected to both the external machine and the signal acquisition device. The host computer is used to implement the above-described method.

[0085] Figure 2 A schematic diagram of a state assessment system according to an embodiment of the present invention is shown. In this embodiment, the invasive brain-computer interface system is a cochlear implant sound processor 210. The external unit of the cochlear implant sound processor 210 is connected to a host computer 220 via a data cable, and the host computer 220 is connected to a signal acquisition device 230 via a data cable. The signal acquisition device 230 acquires surface artifact signals by placing positive and negative signal electrodes near the implant and on the forehead of the implant recipient.

[0086] According to another aspect of the present invention, a computer-readable storage medium is also provided. The storage medium stores a computer program / instructions that, when executed by a processor, implement the method described above. The storage medium may, for example, include a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disc read-only memory (CD-ROM), a USB memory, or any combination of the above storage media. The computer-readable storage medium may be any combination of one or more computer-readable storage media.

[0087] Those skilled in the art will readily understand the implementation structure, working principle, and beneficial effects of electronic devices and computer-readable storage media by reading the above methods. For the sake of brevity, further details will not be elaborated upon here.

[0088] Although exemplary embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above exemplary embodiments are merely illustrative and are not intended to limit the scope of the invention. Various changes and modifications can be made therein by those skilled in the art without departing from the scope and spirit of the invention. All such changes and modifications are intended to be included within the scope of the invention as claimed in the appended claims.

[0089] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0090] In the several embodiments provided by this invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed.

[0091] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0092] Similarly, it should be understood that, in order to streamline the invention and aid in understanding one or more of the various aspects of the invention, features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof in the description of exemplary embodiments of the invention. However, this approach should not be construed as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the corresponding claims, its inventive point lies in solving the corresponding technical problem with fewer features than all of those in a single disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of the invention.

[0093] Those skilled in the art will understand that, apart from the mutual exclusion of features, all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or elements of any method or apparatus so disclosed may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0094] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features but not others included in other embodiments, combinations of features from different embodiments are intended to be within the scope of the invention and form different embodiments. For example, in the claims, any of the claimed embodiments can be used in any combination.

[0095] The various component embodiments of the present invention can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some modules in the electronic device according to embodiments of the present invention. The present invention can also be implemented as an apparatus program (e.g., a computer program and computer program product) for performing some or all of the methods described herein. Such programs implementing the present invention can be stored on a computer-readable medium or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0096] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

[0097] The above description is merely a specific embodiment of the present invention or an explanation of that embodiment. The scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. The scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for state assessment in an invasive brain-computer interface system, characterized in that, The invasive brain-computer interface system includes an external unit and an implant; the method includes: A test sequence is randomly generated, and the test sequence includes multiple stimulation current intensity values; Each of the stimulation current intensity values ​​is sequentially sent to the external device, and the artifact signal on the body surface is acquired simultaneously. Each time the external device receives the stimulation current intensity value, it generates a corresponding stimulation command and sends it to the implant to control the implant to apply electrical stimulation according to the stimulation current intensity value. Based on the surface artifact signal corresponding to each of the stimulation current intensity values, a state assessment result of the invasive brain-computer interface system is generated, and the state assessment result includes at least one of signal validity, abnormal signal amplitude, and waveform distortion.

2. The method according to claim 1, characterized in that, For each of the stimulation current intensity values, the surface artifact signal corresponding to the stimulation current intensity value is determined based on the surface artifact signal acquired within a first preset time period after the stimulation current intensity value is emitted. The process of generating a state assessment result for the invasive brain-computer interface system based on the surface artifact signal corresponding to each of the stimulation current intensity values ​​includes: Determine whether the artifact signal on the body surface corresponding to each of the stimulation current intensity values ​​is a valid signal; The validity of the signal is represented by at least one of the following data: the total number of valid signals, the total number of invalid signals, and the bit error rate, wherein the total number of invalid signals is the difference between the total number of signals and the total number of valid signals, and the bit error rate is the ratio of the total number of invalid signals to the total number of signals.

3. The method according to claim 2, characterized in that, Determining whether the surface artifact signal corresponding to each of the stimulation current intensity values ​​is a valid signal includes: For any of the stimulation current intensity values ​​corresponding to the surface artifact signal, determine whether the peak amplitude of the surface artifact signal is greater than the weighting value of the baseline noise; The surface artifact signal is determined to be a valid signal at least when the peak amplitude of the signal is greater than the weighting value of the baseline noise.

4. The method according to claim 2, characterized in that, The process of generating a state assessment result for the invasive brain-computer interface system based on the surface artifact signal corresponding to each of the stimulation current intensity values ​​includes: For any of the aforementioned stimulation current intensity values, the actual peak-to-peak value of the surface artifact signal is determined when the surface artifact signal is a valid signal. Determine the expected peak-to-peak value corresponding to the intensity of the stimulation current; The amplitude deviation is determined based on the actual peak-to-peak value and the expected peak-to-peak value. When the amplitude deviation is greater than the deviation threshold, the amplitude of the artifact signal on the body surface is determined to be abnormal. The abnormal signal amplitude is represented by at least one of the following data: the number of amplitude abnormality commands and the average amplitude deviation, wherein the number of amplitude abnormality commands is the total number of stimulation current intensity values ​​corresponding to the abnormal amplitude of the surface artifact signal, and the average amplitude deviation is the mean of the amplitude deviation corresponding to each valid signal.

5. The method according to claim 4, characterized in that, The method further includes: Each stimulation current intensity value in the calibration sequence is sent to the external machine in sequence, and the artifact signal on the body surface is acquired simultaneously. The calibration sequence is obtained by the following method: starting with a preset minimum stimulation current, the stimulation current intensity value is increased step by step according to a preset step size until the preset maximum stimulation current is reached. Determine the calibration peak-to-peak value of the surface artifact signal corresponding to each stimulus current intensity value in the calibration sequence; Based on each stimulation current intensity value in the calibration sequence and its corresponding calibration peak value, the relationship between the stimulation current intensity value and the calibration peak value is determined to obtain a preset fitting relationship; The step of determining the expected peak-to-peak value corresponding to the stimulation current intensity value includes: substituting the stimulation current intensity value into the preset fitting relationship to obtain the expected peak-to-peak value.

6. The method according to claim 2, characterized in that, The process of generating a state assessment result for the invasive brain-computer interface system based on the surface artifact signal corresponding to each of the stimulation current intensity values ​​includes: For any of the aforementioned stimulation current intensity values, when the surface artifact signal is a valid signal, it is determined whether the similarity between the surface artifact signal and the baseline template corresponding to the stimulation current intensity value is less than the similarity threshold. When the similarity is less than the similarity threshold, the waveform of the artifact signal on the body surface is determined to be distorted. The total number of artifact signals on the body surface that cause waveform distortion is counted to obtain the waveform distortion count; The waveform distortion condition includes the number of waveform distortions and at least one of the following: average waveform correlation coefficient and waveform distortion rate; wherein the average waveform correlation coefficient is the mean of the similarity corresponding to each valid signal.

7. The method according to any one of claims 2-6, characterized in that, The first preset time period is determined in the following way: The preset stimulation current intensity value is sent to the external machine, and the artifact signal on the body surface is acquired simultaneously to obtain the waveform template. Based on the waveform template, the first preset time period is determined, wherein the start time of the first preset time period is the time difference between the time when the preset stimulation current intensity value is emitted and the time when the signal value in the waveform template begins to deviate from the baseline, and the end time of the first preset time period is the time difference between the time when the signal value in the waveform template completely returns to the baseline noise level and the time when the signal value in the waveform template begins to deviate from the baseline.

8. The method according to claim 1, characterized in that, Before generating the state assessment result of the invasive brain-computer interface system based on the surface artifact signal corresponding to each of the stimulation current intensity values, the method further includes: The surface artifact signal obtained from each transmission of the stimulation current intensity value is filtered using a high-pass filter. or, Baseline signals are continuously acquired during a second preset time period before the stimulation current intensity value is sent, and the signal mean is calculated; For each time the stimulation current intensity value is sent, the surface artifact signal obtained is subtracted from the signal mean point by point to achieve baseline correction.

9. A state assessment system for invasive brain-computer interface systems, characterized in that, The invasive brain-computer interface system includes an external unit and an implant; the status assessment system includes: A host computer and a signal acquisition device; the signal acquisition device is used to acquire surface artifact signals; the host computer is connected to the external device and the signal acquisition device respectively; the host computer is used to implement the method described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, The system stores a computer program / instructions that, when executed by a processor, implement the method as described in any one of claims 1-8.

Images