CN-122004877-A - State evaluation method, system and medium for invasive brain-computer interface system

CN122004877ACN 122004877 ACN122004877 ACN 122004877ACN-122004877-A

Abstract

The invention provides a state evaluation method, a state evaluation system and a state evaluation medium for an invasive brain-computer interface system. The method comprises the steps of randomly generating a test sequence, wherein the test sequence comprises a plurality of stimulation current intensity values, sequentially sending each stimulation current intensity value to an external machine, and synchronously obtaining body surface artifact signals, wherein the external machine generates corresponding stimulation instructions and sends the corresponding stimulation instructions to an implant body when receiving the stimulation current intensity values each time so as to control the implant body to apply electric stimulation according to the stimulation current intensity values, and generating a state evaluation result of an invasive brain-computer interface system based on the body surface artifact signals corresponding to each stimulation current intensity value, wherein the state evaluation result comprises at least one of signal effectiveness, signal amplitude abnormal conditions and waveform distortion conditions. The method objectively and accurately evaluates the working state of the invasive brain-computer interface system.

Inventors

Dai Zhuangzhuang
CHEN CHAOQUN
WANG CHENG
LIN HEPING
YE YU

Assignees

上海力声特医学科技有限公司

Dates

Publication Date: 20260512
Application Date: 20260305

Claims (10)

1. A method for state assessment of an invasive brain-computer interface system, the invasive brain-computer interface system comprising an external machine and an implant, the method comprising: randomly generating a test sequence comprising a plurality of stimulus current intensity values; Sequentially sending each stimulation current intensity value to the external machine, and synchronously obtaining a body surface artifact signal, wherein the external machine generates a corresponding stimulation instruction and sends the corresponding stimulation instruction to the implant when receiving the stimulation current intensity value each time so as to control the implant to apply electric stimulation according to the stimulation current intensity value; Based on the body surface artifact signals corresponding to each stimulation current intensity value, generating a state evaluation result of the invasive brain-computer interface system, wherein the state evaluation result comprises at least one of signal effectiveness, signal amplitude abnormal conditions and waveform distortion conditions.
2. The method of claim 1, wherein for each of the stimulus current intensity values, a body surface artifact signal corresponding to the stimulus current intensity value is determined based on body surface artifact signals acquired during a first preset period of time after the stimulus current intensity value is transmitted; the generating a state evaluation result of the invasive brain-computer interface system based on the body surface artifact signals corresponding to each stimulation current intensity value includes: determining whether the body surface artifact signals corresponding to the stimulation current intensity values are effective signals or not; the signal validity is represented by at least one of the total number of valid signals, the total number of invalid signals, and an 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 error rate is the ratio of the total number of invalid signals to the total number of signals.
3. The method of claim 2, wherein determining whether the body surface artifact signal corresponding to each of the stimulation current intensity values is a valid signal comprises: Judging whether the signal peak amplitude of the body surface artifact signal corresponding to any stimulation current intensity value is larger than the weighting value of the baseline noise or not; and determining the body surface artifact signal as a valid signal at least when the signal peak amplitude of the body surface artifact signal is greater than the weighted value of the baseline noise.
4. The method of claim 2, wherein generating the state evaluation result of the invasive brain-computer interface system based on the body surface artifact signal corresponding to each of the stimulus current intensity values comprises: for any body surface artifact signal corresponding to the stimulation current intensity value, determining an actual peak value of the body surface artifact signal when the body surface artifact signal is an effective signal; determining an expected peak value corresponding to the stimulation current intensity value; Determining an amplitude deviation based on the actual peak-to-peak value and the expected peak-to-peak value; when the amplitude deviation is larger than a deviation threshold value, determining that the amplitude of the body surface artifact signal is abnormal; The signal amplitude abnormality is represented by at least one of an amplitude abnormality instruction number which is the total number of stimulation current intensity values of the corresponding body surface artifact signal amplitude abnormality and an average amplitude deviation which is the average value of the amplitude deviation corresponding to each effective signal.
5. The method according to claim 4, wherein the method further comprises: Sequentially sending each stimulation current intensity value in a calibration sequence to the external machine, and synchronously obtaining a body surface artifact signal, wherein the calibration sequence is obtained by starting with a preset minimum stimulation current, and increasing the stimulation current intensity value according to a preset step length until reaching a preset maximum stimulation current; determining a calibration peak value of the body surface artifact signal corresponding to each stimulation current intensity value in the calibration sequence; Based on each stimulation current intensity value in the calibration sequence and the corresponding calibration peak value, determining the relation between the stimulation current intensity value and the calibration peak value so as to obtain a preset fitting relation; The step of determining the expected peak value corresponding to the stimulation current intensity value comprises the step of bringing the stimulation current intensity value into the preset fitting relation to obtain the expected peak value.
6. The method of claim 2, wherein generating the state evaluation result of the invasive brain-computer interface system based on the body surface artifact signal corresponding to each of the stimulus current intensity values comprises: For any body surface artifact signal corresponding to the stimulation current intensity value, judging whether the similarity between the body surface artifact signal and a baseline template corresponding to the stimulation current intensity value is smaller than a similarity threshold value when the body surface artifact signal is an effective signal; When the similarity is smaller than a similarity threshold value, determining waveform distortion of the body surface artifact signal; counting the total number of waveform distortion body surface artifact signals to obtain waveform distortion numbers; the waveform distortion condition comprises at least one of a waveform distortion number and at least one of average waveform correlation coefficient and waveform distortion rate, wherein the average waveform correlation coefficient is the average value of the similarity corresponding to each effective signal.
7. The method according to any of claims 2-6, wherein the first preset period is determined by: transmitting a preset stimulation current intensity value to the external machine, and synchronously acquiring body surface artifact signals to obtain a waveform template; And determining the first preset period according to the waveform template, wherein the starting time of the first preset period is the time difference between the sending time of the preset stimulation current intensity value and the time when the signal value in the waveform template starts to deviate from a base line, and the ending time of the first preset period is the time difference between the time when the signal value in the waveform template completely returns to the base line noise level and the time when the signal value in the waveform template starts to deviate from the base line.
8. The method of claim 1, wherein prior to generating the state assessment result for the invasive brain-computer interface system based on the body surface artifact signals for each of the stimulation current intensity values, the method further comprises: filtering the body surface artifact signals obtained by sending the stimulating current intensity values each time by using a high-pass filter; Or alternatively, the first and second heat exchangers may be, Continuously acquiring a baseline signal in a second preset period before the stimulation current intensity value is sent, and calculating a signal average value; and subtracting the signal mean value from the body surface artifact signal point by point for the body surface artifact signal obtained by sending the stimulation current intensity value each time so as to realize baseline correction.
9. A state assessment system for an invasive brain-computer interface system, the invasive brain-computer interface system comprising an external machine and an implant, the state assessment system comprising: the device comprises an upper computer and a signal collector, wherein the signal collector is used for collecting body surface artifact signals, the upper computer is respectively connected with the external machine and the signal collector, and the upper computer is used for realizing the method of any one of claims 1-8.
10. A computer readable storage medium, characterized in that a computer program/instruction is stored, which, when executed by a processor, implements the method according to any of claims 1-8.

Description

State evaluation method, system and medium for invasive brain-computer interface system Technical Field The invention relates to the technical field of invasive brain-computer interface systems, in particular to a state evaluation method, a state evaluation system and a state evaluation medium for an invasive brain-computer interface system. Background Invasive brain-computer interface systems directly record neural electrical activity or apply electrical stimulation by implanting an electrode array within the nervous system to restore or enhance impaired nerve function. Its proper functioning relies on stable, reliable wireless (or percutaneous wired) data and energy transmission between an external processor (an external machine) and an internal implant. After receiving the coded control instructions, the implant applies accurate electric pulse stimulation to the target nerve tissue through the electrode array of the implant. Currently, the evaluation of the working state of an invasive brain-computer interface system mainly depends on subjective feedback. The subjective detection depends on active feedback of a patient, whether the implant accurately executes each stimulation instruction cannot be intuitively verified, whether the cause of abnormality is insufficient neural response or incorrect instruction execution of the implant is difficult to distinguish when the evaluation result is abnormal, and therefore problem positioning efficiency is reduced. In view of this, the present invention has been made. Disclosure of Invention The present invention has been made in view of the above-described problems. According to one aspect of the present invention, there is provided a state assessment method for an invasive brain-computer interface system comprising an external machine and an implant, the method comprising: randomly generating a test sequence comprising a plurality of stimulus current intensity values; Sequentially sending each stimulation current intensity value to the external machine, and synchronously obtaining a body surface artifact signal, wherein the external machine generates a corresponding stimulation instruction and sends the corresponding stimulation instruction to the implant when receiving the stimulation current intensity value each time so as to control the implant to apply electric stimulation according to the stimulation current intensity value; Based on the body surface artifact signals corresponding to each stimulation current intensity value, generating a state evaluation result of the invasive brain-computer interface system, wherein the state evaluation result comprises at least one of signal effectiveness, signal amplitude abnormal conditions and waveform distortion conditions. For each stimulation current intensity value, the body surface artifact signal corresponding to the stimulation current intensity value is determined based on the body surface artifact signal acquired in a first preset period after the stimulation current intensity value is transmitted; the generating a state evaluation result of the invasive brain-computer interface system based on the body surface artifact signals corresponding to each stimulation current intensity value includes: determining whether the body surface artifact signals corresponding to the stimulation current intensity values are effective signals or not; the signal validity is represented by at least one of the total number of valid signals, the total number of invalid signals, and an 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 error rate is the ratio of the total number of invalid signals to the total number of signals. Illustratively, the determining whether the body surface artifact signal corresponding to each stimulation current intensity value is a valid signal includes: Judging whether the signal peak amplitude of the body surface artifact signal corresponding to any stimulation current intensity value is larger than the weighting value of the baseline noise or not; and determining the body surface artifact signal as a valid signal at least when the signal peak amplitude of the body surface artifact signal is greater than the weighted value of the baseline noise. Illustratively, the generating a state evaluation result of the invasive brain-computer interface system based on the body surface artifact signals corresponding to each stimulation current intensity value includes: for any body surface artifact signal corresponding to the stimulation current intensity value, determining an actual peak value of the body surface artifact signal when the body surface artifact signal is an effective signal; determining an expected peak value corresponding to the stimulation current intensity value; Determining an amplitude deviation based on the actual peak-to-peak value and the expected peak-to-peak value; when the amplitud