WO2023134720A1 - 刺激模式的控制方法、控制系统、电子设备及介质 - Google Patents

刺激模式的控制方法、控制系统、电子设备及介质 Download PDF

Info

Publication number
WO2023134720A1
WO2023134720A1 PCT/CN2023/071875 CN2023071875W WO2023134720A1 WO 2023134720 A1 WO2023134720 A1 WO 2023134720A1 CN 2023071875 W CN2023071875 W CN 2023071875W WO 2023134720 A1 WO2023134720 A1 WO 2023134720A1
Authority
WO
WIPO (PCT)
Prior art keywords
stimulation
propagation
early warning
mode
control method
Prior art date
Application number
PCT/CN2023/071875
Other languages
English (en)
French (fr)
Inventor
黄肖山
刘晓玲
胥红来
章希睿
刘涛
任思瑾
李含磊
Original Assignee
博睿康医疗科技(上海)有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 博睿康医疗科技(上海)有限公司 filed Critical 博睿康医疗科技(上海)有限公司
Publication of WO2023134720A1 publication Critical patent/WO2023134720A1/zh

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
    • A61N1/00—Electrotherapy; Circuits therefor
    • A61N1/18—Applying electric currents by contact electrodes
    • A61N1/32—Applying electric currents by contact electrodes alternating or intermittent currents
    • A61N1/36—Applying electric currents by contact electrodes alternating or intermittent currents for stimulation
    • A61N1/3605—Implantable neurostimulators for stimulating central or peripheral nerve system
    • A61N1/3606—Implantable neurostimulators for stimulating central or peripheral nerve system adapted for a particular treatment
    • A61N1/36062—Spinal stimulation
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/369—Electroencephalography [EEG]
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/74—Details of notification to user or communication with user or patient ; user input means
    • A61B5/746—Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
    • A61N1/00—Electrotherapy; Circuits therefor
    • A61N1/18—Applying electric currents by contact electrodes
    • A61N1/32—Applying electric currents by contact electrodes alternating or intermittent currents
    • A61N1/36—Applying electric currents by contact electrodes alternating or intermittent currents for stimulation
    • A61N1/3605—Implantable neurostimulators for stimulating central or peripheral nerve system
    • A61N1/3606—Implantable neurostimulators for stimulating central or peripheral nerve system adapted for a particular treatment
    • A61N1/36064—Epilepsy
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
    • A61N1/00—Electrotherapy; Circuits therefor
    • A61N1/18—Applying electric currents by contact electrodes
    • A61N1/32—Applying electric currents by contact electrodes alternating or intermittent currents
    • A61N1/36—Applying electric currents by contact electrodes alternating or intermittent currents for stimulation
    • A61N1/3605—Implantable neurostimulators for stimulating central or peripheral nerve system
    • A61N1/3606—Implantable neurostimulators for stimulating central or peripheral nerve system adapted for a particular treatment
    • A61N1/36067—Movement disorders, e.g. tremor or Parkinson disease
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
    • A61N1/00—Electrotherapy; Circuits therefor
    • A61N1/18—Applying electric currents by contact electrodes
    • A61N1/32—Applying electric currents by contact electrodes alternating or intermittent currents
    • A61N1/36—Applying electric currents by contact electrodes alternating or intermittent currents for stimulation
    • A61N1/3605—Implantable neurostimulators for stimulating central or peripheral nerve system
    • A61N1/36128—Control systems
    • A61N1/36135—Control systems using physiological parameters
    • A61N1/36139—Control systems using physiological parameters with automatic adjustment

Definitions

  • the invention relates to the technical field of time series data processing, in particular to a stimulation mode control method, control system, electronic equipment and media.
  • Nerve electrical stimulation technology uses surgery to implant electrodes in specific areas of the brain or spinal cord, and regulates the activities of related neurons through electrical stimulation, so as to achieve the purpose of treating neurological diseases.
  • Nerve electrical stimulation technology has the advantages of being relatively safe, reversible, and postoperatively adjustable compared with traditional damage surgery, and has achieved remarkable curative effects in some neurological diseases such as epilepsy and Parkinson's disease.
  • the technical problem to be solved by the present invention is to provide a stimulation mode control method, control system, electronic equipment and medium.
  • control method of the stimulation mode includes: constructing a specific data set of the measured physiological signal; judging whether the physiological signal to be measured belongs to the specific data set; stimulation mode.
  • the physiological signal is detected by using multiple leads;
  • the specific data set includes: the propagation mode of the measured physiological signal and its occurrence probability; wherein the propagation mode includes: the number of early warning channels of the physiological signal, the timing of early warning propagation at least one of the
  • the judging whether the physiological signal to be tested belongs to the specific data set includes: when the number of warning channels of the physiological signal to be tested is greater than or equal to the set threshold of the number of warning channels, the judgment result is "yes"; and/or when When the early warning propagation timing of the physiological signal to be measured meets the set threshold matching the early warning propagation timing, the judgment result is "Yes".
  • the determination priority of the number of early warning channels is higher than the timing of early warning propagation.
  • the matching priority of the stimulation pattern is the difference in the number of early warning channels, the matching similarity of the early warning propagation time sequence, and the occurrence probability of the propagation pattern.
  • the stimulation mode includes stimulation parameters; the stimulation parameters include at least one of the intensity, pulse width, frequency, and charge density of the stimulation waveform.
  • the present invention provides a stimulation mode control system for running the above-mentioned control method, including: a host computer, which is used to construct the specific data set; a lower computer, which is used to store the specific data set, and judge whether the physiological signal to be tested belongs to the specific data set, so as to select a matching stimulation mode.
  • the lower computer includes: an acquisition module, a matching module, an early warning module, a judgment module and a warning module; when the judgment result is "No", the lower computer controls the warning module to warn;
  • the upper computer includes: data Load modules, compute modules, and setup modules.
  • the present invention provides an electronic device, including: a processor and a memory, the memory is used to store machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the The memories are in a communication connection, and the machine-readable instructions are executed by the processor to execute the above-mentioned control method.
  • the present invention provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is run by a processor, the above-mentioned control method is executed.
  • the beneficial effect of the present invention is that the control method and control system of the stimulation mode of the present invention can obtain the early warning results of real-time time series data of multiple channels or leads through the early warning algorithm, comprehensively judge whether to implement stimulation according to the early warning results, and select a matching
  • the stimulation mode can be used to stimulate, which can improve the accuracy of stimulation.
  • Fig. 1 is a working flowchart of the control method of the stimulation mode of the present invention.
  • Fig. 2 is a schematic diagram of the propagation matrix of the present invention.
  • Fig. 3 is a schematic diagram of the clustering result of the similarity matrix of the present invention.
  • Fig. 4 is a schematic diagram of the first propagation mode and its occurrence probability in the present invention.
  • Fig. 5 is a schematic diagram of the second propagation mode and its occurrence probability in the present invention.
  • Fig. 6 is a schematic diagram of the third propagation mode and its occurrence probability in the present invention.
  • Fig. 7 is a structural schematic diagram of the control system of the stimulation mode of the present invention.
  • Fig. 8 is a schematic diagram of the processing result of the clustering algorithm of the present invention on the electromyographic signal.
  • Fig. 9 is a schematic diagram of the processing result of the epilepsy signal by the clustering algorithm of the present invention.
  • Fig. 10 is a characteristic comparison diagram of the EMG signal and the epilepsy signal of the present invention.
  • connection should be understood in a broad sense, for example, it can be a fixed connection or a detachable connection. Connected, or integrally connected; it may be mechanically connected or electrically connected; it may be directly connected or indirectly connected through an intermediary, and it may be the internal communication of two components.
  • first and second may explicitly or implicitly include one or more of these features.
  • plural means two or more. Those of ordinary skill in the art can understand the specific meanings of the above terms in the present invention in specific situations.
  • the physiological signals such as but not limited to EEG signals
  • EEG signals can be matched with different stimulation modes through the control system to adapt to various neurological diseases.
  • EEG signal of epilepsy as an example, The method of controlling the stimulation pattern in this case will be described in detail.
  • Epilepsy states can generally be divided into four states: interictal, preictal, ictal, and postictal.
  • the interictal period represents the EEG signal of the patient in a normal state
  • the preictal period represents the EEG signal of the patient for a period of time before the onset of the onset
  • the ictal period represents the EEG signal of the patient during the seizure
  • the postictal period represents the period after the patient’s seizure EEG signals over time. Since the EEG signals in the pre-seizure period are more active than the normal EEG signals, the EEG signals in the pre-seizure period can be used for early warning of epileptic seizures.
  • the present invention provides a method for controlling stimulation patterns, which mainly includes the following steps: constructing a specific data set of the measured physiological signal; judging whether the measured physiological signal belongs to the specific data set; ", start the stimulation and select the matching stimulation mode; when the judgment result is "No", give a warning or disable the stimulation.
  • the matching stimulation mode can also be selected through the manual operation control system.
  • the physiological signal is detected using multiple channels;
  • the specific data set includes: the propagation mode and occurrence probability of the measured physiological signal;
  • the propagation mode includes: at least one of the number of early warning channels of the physiological signal and the timing of early warning propagation.
  • the specific operation process of the stimulation mode control method is as follows: S1: Obtain several propagation modes and the occurrence probability of each propagation mode to form a specific data set. S2: Select at least one propagation mode in a specific data set and set a one-to-one corresponding stimulation mode. S3: multiple channels output multiple warning results at the same time, and judge whether to start stimulation according to the multiple warning results; if the judgment result is "yes", use the stimulation mode to stimulate the target object.
  • multiple electrodes that is, multiple channels or leads
  • multiple electrodes can be respectively arranged at different positions of the brain of the target subject for brain monitoring.
  • one channel corresponds to one electrode.
  • the EEG signal changes monitored by multiple channels will be carried out in a certain order, and the number of channels can be understood
  • the sequence of changes in the position of this channel can be understood as the timing of epilepsy transmission, and the two form the transmission mode of epilepsy.
  • channel 1 there are 5 channels in total, respectively recorded as channel 1, channel 2, channel 3, channel 4 and channel 5, and each channel corresponds to a different position of the target subject's brain.
  • channel 2 first detects the EEG signals in the pre-seizure period, and as time goes by, channel two, channel three, channel four and channel five then monitor the EEG signals in the pre-seizure stage in sequence.
  • the epilepsy propagation sequence is "channel One ⁇ Channel Two ⁇ Channel Three ⁇ Channel Four ⁇ Channel Five".
  • the epileptic seizure propagation sequence can also be "channel one ⁇ channel three ⁇ channel two ⁇ channel four ⁇ channel five" or "channel one ⁇ channel three ⁇ channel four ⁇ channel two ⁇ channel five” and so on.
  • the number of early-warning channels in epilepsy can reflect the number of channels of EEG signals in the pre-seizure stage; the timing of early-warning transmission in epilepsy can reflect the channel order of EEG signal changes in the pre-seizure state.
  • the host computer send the measured EEG data to the host computer, and use the number of early warning channels (that is, the number of channels that generate early warnings) and the probability of occurrence or the timing of early warning propagation (that is, the time sequence that generates early warnings) to construct a specific data set.
  • the number of early warning channels that is, the number of channels that generate early warnings
  • the probability of occurrence or the timing of early warning propagation that is, the time sequence that generates early warnings
  • Step S1 Obtain several propagation modes and the probability of occurrence of each propagation mode to form a specific data set.
  • the previous historical data is processed by a clustering algorithm to obtain several propagation modes and the probability of occurrence of each propagation mode.
  • the historical data includes EEG data at different locations monitored by multiple channels, and the clustering algorithm may be, for example, a propagation matrix similarity clustering algorithm, and the historical data is processed through the clustering algorithm, which specifically includes the following steps.
  • Preprocessing Perform band-pass filtering on the historical data monitored by all channels to filter out For the historical data interval segment in the early stage of epileptic seizures, use a sliding window with a width of t 1 to sequentially take out multiple segments of the historical data interval segment, and perform root mean square (RMS) processing on each segment, so that the waveform of the historical data Smoother.
  • RMS root mean square
  • Convolution is the result of multiplying two variables within a certain range and summing them up. Arrange multiple channels in pairs, use a sliding window with a window width of t 2 and a step of ⁇ t, and sequentially select data segments from the data monitored by the two channels, assuming that both channels can select M data Segments, denoted as M a and M b respectively, perform pairwise convolution between the data segments Ma and M b .
  • M a1 performs convolution operations with M b1 , M b2 , M b3 , ... M bj respectively
  • M a2 performs convolution operations with M b1 , M b2 , M b3 , ... M bj respectively, so that By analogy, convolution operations are performed on Mai and M b1 , M b2 , M b3 , .
  • propagation matrix set the channel number as N, repeat steps S11 to S14, can obtain T N * N dimension propagation matrices (as shown in Figure 2), the numerical value in the propagation matrix can be concrete time difference value or will The time difference value after binarization.
  • the horizontal axis of the propagation matrix represents the jth channel (1 ⁇ i ⁇ N), and the vertical axis of the propagation matrix represents the ith channel (1 ⁇ j ⁇ N). If the value in the propagation matrix is non-zero, it indicates that the jth channel There is a link relationship between the first channel and the i-th channel, if the value in the propagation matrix is "1", it indicates that the propagation order of the j-th channel is before the i-th channel.
  • Propagation matrix similarity vectorize each propagation matrix to obtain a pair of propagation matrices The corresponding vector, and then calculate the similarity between the two vectors.
  • the calculation method of the similarity can be, for example, Pearson correlation coefficient, Euclidean distance, etc., which can be selected according to the actual situation.
  • Similarity matrix taking the similarity between two T propagation matrices as elements, a T ⁇ T-dimensional similarity matrix can be obtained.
  • Similarity matrix clustering clustering the similarity matrix can obtain several stereotyped propagation modes and the occurrence probability of each propagation mode. For example, as shown in FIG. 3 , K1 , K2 , and K3 represent the frequency of occurrence of propagation mode 1, propagation mode 2, and propagation mode 3, respectively. Each propagation mode represents the linkage relationship between the data of N channels respectively. According to the occurrence frequency of different propagation modes, the probability of occurrence of each propagation mode is calculated.
  • the probability of occurrence of propagation mode 1 is K 1 /(K 1 +K 2 +K 3 ), and the probability of occurrence of propagation mode 2 is K 2 /(K 1 +K 2 +K 3 ) , the probability of occurrence of propagation mode 3 is K 3 /(K 1 +K 2 +K 3 ), and the start time corresponding to each propagation mode is also different, for example, the start time corresponding to propagation mode 1 is 0- 12ms, the start time corresponding to propagation mode 2 is 0-70 ms, and the start time corresponding to propagation mode 3 is 0-7 ms, indicating that the occurrence time of each propagation mode is also different.
  • a specific data set is composed of several propagation modes obtained through the above steps and the occurrence probability of each propagation mode, and stored in the host computer. It should be noted that the user can select, edit, create and save the transmission mode, stimulation mode or stimulation effect parameters saved in the host computer. If the user thinks that the existing transmission mode in the host computer does not meet the requirements, he can create a new one. Or edit the propagation mode. After creating or editing, the host computer can automatically recalculate the probability of each propagation mode according to the new propagation mode.
  • Step S2 Select at least one propagation mode in a specific data set and set a corresponding stimulation mode.
  • the user selects at least one of the transmission modes displayed in the host computer, and sets the corresponding stimulation mode according to the selected transmission mode, for example, the intensity and pulse width of the stimulation waveform can be set. Degree, frequency, charge density and other parameters (ie stimulation parameters). After setting, you need to click the "Validate" button, so that the selected transmission mode and corresponding stimulation mode will be transmitted to the lower computer or the internal computer.
  • Step S3 multiple channels output multiple warning results at the same time, and judge whether to start stimulation according to the multiple warning results; if the judgment result is "yes", use the stimulation mode to stimulate the target object.
  • judging whether the physiological signal to be tested belongs to a specific data set includes: when the number of warning channels of the physiological signal to be tested is greater than or equal to the set threshold value of the number of warning channels, the judgment result is "yes”; and/or when the physiological signal to be tested When the timing of the early warning propagation matches the setting value of the early warning propagation timing, the judgment result is "Yes".
  • the judgment priority of the number of early warning channels is higher than the timing of early warning propagation, that is, when the number of early warning channels is greater than the set threshold of the number of early warning channels, the judgment result must be "yes", and the judgment process at this time no longer considers whether the timing of early warning propagation is match.
  • the matching priority of the stimulus pattern is the difference in the number of early warning channels, the matching degree of the early warning propagation time sequence, and the occurrence probability of the propagation pattern.
  • the transmission mode of epilepsy will be compared with the transmission mode corresponding to the stimulation mode in a specific data set, and the stimulation mode with the smallest difference in the number of warning channels will be selected first, followed by the highest matching degree of warning transmission timing, and finally is the propagation mode with the highest probability of occurrence.
  • the epilepsy early warning algorithm can be used to judge the real-time time series data collected by each channel for epilepsy early warning.
  • the output early warning results include whether to start early warning or not. If the warning result is start warning, record the number of corresponding warning channels and the time sequence of warning dissemination.
  • epilepsy early warning algorithms There are many kinds of epilepsy early warning algorithms according to the actual situation. The steps of an epilepsy early warning algorithm are listed here, including: T1: preprocessing the raw EEG data collected in real time from multiple channels; T2: calculating the signal characteristics of the EEG data; T3: Classify the EEG data according to the signal characteristics, and output the early warning results.
  • the preprocessing in step T1 includes noise reduction, downsampling and multi-window division. multiple windows
  • the window division can adopt the manner that the windows partially overlap or do not overlap.
  • the purpose of multi-window division is to select a sequence segment of EEG data each time.
  • the characteristic signal in step T2 is, for example, the zero-crossing coefficient, the zero-crossing coefficient is a mapping of zero-crossing rate or zero-crossing number; the mapping is a mapping function with positive or negative correlation; and the mapping function is linear or nonlinear.
  • the zero-crossing coefficient can reflect the frequency of zero-crossing points of data values in the sequence segment of the EEG signal.
  • *x(2:N) means point-to-point multiplication between two arrays, num ⁇ x(1:N-1).*x(2:N) ⁇ 0 ⁇ /(N- 1) Indicates the probability that the result of point-to-point multiplication is less than 0, that is, the zero-crossing rate.
  • the zero-crossing rate is mapped to a value range of 0 Zero-crossing coefficient between -1.
  • the larger the zero-crossing coefficient the lower the activity of EEG data oscillation, and the smaller the zero-crossing coefficient, the higher the activity of EEG data oscillation.
  • the output "1" of the classifier indicates that the EEG signal segment is in a pre-seizure state
  • the output "0" indicates that the EEG signal segment is in a normal state.
  • start stimulation which specifically includes: S31: sort the warning time to obtain the actual warning propagation sequence, S32: if the number N SZ of warning channels is greater than or equal to the first threshold N, then Start stimulation directly; S32: If the number N SZ of warning channels is less than the first threshold N, then match the actual early warning propagation timing with the propagation mode, and if the matching result shows that the actual early warning propagation timing is a subset of the propagation mode, then start the stimulus.
  • the multiple recorded warning moments are sorted in ascending or descending order (consistent with the time sequence of the propagation mode), and the actual warning propagation time sequence is generated, and the number of warning channels is recorded at the same time. If the number N SZ of early warning channels is greater than or equal to the first threshold N, the stimulation is directly started, and the stimulation mode preset in step S2 is used for stimulation. If the number N SZ of early warning channels is less than the first threshold N, the actual early warning timing is matched with the propagation mode, and if the matching result is that the actual early warning propagation timing is a subset of the propagation mode, the stimulation is started.
  • the propagation mode is essentially a time sequence, which is spliced together by the moments of multiple channels.
  • the timing sequence of the propagation mode is 12345, if the actual warning timing is a subset such as 123 or 234, it is also necessary to start the stimulus.
  • stimulating adopt the stimulation mode preset in step S2. The user can repeat steps S1 to S3 according to the stimulation effect.
  • the present invention also provides a stimulation mode control system, which runs the above stimulation mode control method.
  • the system includes an upper computer 1 and a lower computer 2 .
  • the host computer 1 (such as remote terminal, CPU, cloud server) is used to obtain, save and display specific data sets, and set stimulation modes.
  • the lower computer 2 (such as a computer, a processor) is used to store the specific data set, and judge whether the physiological signal to be tested belongs to the specific data set, so as to select a matching stimulation mode.
  • Lower computer comprises: acquisition module 21, matching module 22, early warning module 23, judgment module 24 and warning module 25 (as sound prompt, disable stimulation control circuit etc.); 25 for warning;
  • the upper computer 1 includes: a data loading module 11, a computing module 12 and a setting module 13.
  • control system can also be used for implants, and further includes an internal machine 3 installed in the body of the target subject for collecting real-time time-series data of multiple channels and starting stimulation.
  • the upper computer 1 is connected with the internal machine 3
  • the lower computer 2 is connected with the internal machine 3.
  • the collection module 21 is used for receiving the real-time time-series data of the target object collected by the internal machine 3 .
  • the early warning module 23 is used to receive the real-time time-series data acquired by the acquisition module 21, and process the real-time time-series data with an epilepsy early-warning algorithm to obtain the actual early-warning propagation time series and the number of early-warning channels.
  • the judging module 24 is used to judge whether the number N SZ of early warning channels is greater than or equal to a first threshold N, and the size of the first threshold N can be set according to actual conditions.
  • the matching module 22 is used to match the actual warning propagation time sequence with the propagation mode. If the matching result is that the actual warning propagation time sequence is a subset of the propagation mode, the matching result is sent to the internal machine 3, and the internal machine 3 applies stimulation to the target object.
  • the data loading module 11 is connected to the calculation module 12
  • the calculation module 12 is connected to the setting module 13
  • the setting module 13 is connected to the matching module 32 .
  • the data loading module 11 is used for reading and displaying historical data and displaying the number of channels.
  • the calculating module 12 is used for calculating and displaying specific data sets.
  • the upper computer 1 also has a progress bar function, and you can check the calculation progress, because when the calculation amount is relatively large, the display interface may be stuck. Operation needs to be restarted.
  • the setting module 13 is used to select the transmission mode, and can also edit, create and save the transmission mode. At the same time, it can set the corresponding stimulation mode according to the selected transmission mode, and transmit the selected transmission mode and stimulation mode to the body. When the machine 3 and the internal machine 3 apply stimulation, they stimulate according to a preset stimulation mode.
  • the clustering algorithm in the above control method can also be used to process the patient's epilepsy signal and myoelectric signal separately, and obtain the results shown in Figures 8 to 10, so as to distinguish the epilepsy signal from the myoelectric signal and avoid misjudgment and false stimulation.
  • Figure 8 is the original waveform of the EMG signal and the waveform after RMS processing
  • Figure 9 is the original waveform of the epilepsy signal and the waveform after RMS processing. Comparing these two figures, it can be found that the propagation of EMG signals has no timing, while the propagation of epilepsy signals has timing.
  • the number of channels with high link strength in the epilepsy signal is small, and the link strength between channels is relatively concentrated, when The EMG signal has a large number of channels with high link strength, the link strength between channels is relatively scattered, and the time difference is small. It shows that the method can effectively distinguish epilepsy signals and electromyographic signals, and the invention can effectively improve the accuracy of epilepsy stimulation and reduce misjudgment.
  • the present invention also provides an electronic device, including a processor and a memory.
  • the memory is used to store machine-readable instructions executable by the processor.
  • the processor and the memory are connected in communication, and the machine-readable instructions are When executed, the processor executes the steps of the above stimulation mode control method.
  • the present invention also provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and the computer program executes the steps of the above stimulation mode control method when the computer program is run by a processor.
  • the computer-readable medium may be included in the above system, or exist independently.
  • the computer-readable storage medium carries one or more programs which, when executed, implement the described analytical methods.
  • the computer-readable storage medium may be a non-volatile computer-readable storage medium, such as may include but not limited to: portable computer disk, hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable Read memory (EPROM or flash memory), portable compact disk read-only memory (CDROM), optical storage device, magnetic storage device, or any suitable combination of the above, but it is not used to limit the scope of protection of the present application.
  • RAM random access memory
  • ROM read-only memory
  • EPROM or flash memory erasable programmable Read memory
  • CDROM portable compact disk read-only memory
  • optical storage device magnetic storage device, or any suitable combination of the above, but it is not used to limit the scope of protection of the present application.
  • the stimulation mode control method and control system of the present invention combine the propagation mode of the measured physiological signal and the early warning algorithm to construct a specific data set of the measured physiological signal, and then judge whether the physiological signal to be measured belongs to the specific data set; when When the judgment result is "yes", the stimulation is started and the matching stimulation mode is selected, which realizes the effective regulation of the stimulation mode, avoids invalid stimulation and its side effects, and can greatly improve the accuracy and safety of stimulation.
  • the present invention can effectively distinguish epilepsy signals and electromyographic signals, improve the accuracy of epilepsy early warning and epilepsy stimulation, reduce misjudgment, and has high application value.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Veterinary Medicine (AREA)
  • Public Health (AREA)
  • Animal Behavior & Ethology (AREA)
  • Neurology (AREA)
  • Neurosurgery (AREA)
  • Biophysics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Physics & Mathematics (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Surgery (AREA)
  • Molecular Biology (AREA)
  • Physiology (AREA)
  • Medical Informatics (AREA)
  • Pathology (AREA)
  • Psychiatry (AREA)
  • Artificial Intelligence (AREA)
  • Psychology (AREA)
  • Orthopedic Medicine & Surgery (AREA)
  • Hospice & Palliative Care (AREA)
  • Evolutionary Computation (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Physics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Signal Processing (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)

Abstract

一种刺激模式的控制方法、控制系统、电子设备及介质。刺激模式的控制方法包括：构建已测生理信号的特定数据集合；判断待测生理信号是否属于特定数据集合；当判断结果为"是"时，启动刺激并选择匹配的刺激模式，使刺激模式做到有的放矢。刺激模式的控制方法实现了刺激模式的有效调控，提高了刺激的准确率。

Description

刺激模式的控制方法、控制系统、电子设备及介质 技术领域
本发明涉及时序数据处理技术领域，尤其涉及一种刺激模式的控制方法、控制系统、电子设备及介质。
背景技术
神经电刺激技术，是利用外科手术在脑特定区域或脊髓植入电极，通过电刺激调控相关神经元的活动，从而达到治疗神经系统疾病的目的。神经电刺激技术较传统损毁手术具有相对安全、可逆以及术后可调整等优势，已经在癫痫、帕金森症等一些神经系统疾病上取得了显著的疗效。
发明内容
本发明要解决的技术问题是：提供一种刺激模式的控制方法、控制系统、电子设备及介质。
本发明解决其技术问题所采用的技术方案是：
第一方面，所述刺激模式的控制方法包括：构建已测生理信号的特定数据集合；判断待测生理信号是否属于所述特定数据集合；当判断结果为“是”时，启动刺激并选择匹配的刺激模式。
进一步地，所述生理信号采用多个导联检测；所述特定数据集合包括：已测生理信号的传播模式及其出现概率；其中所述传播模式包括：生理信号的预警通道数量、预警传播时序中的至少一种。
进一步地，所述判断待测生理信号是否属于所述特定数据集合包括：当待测生理信号的预警通道数量大于或等于预警通道数量的设置阈值时，判断结果为“是”；和/或当待测生理信号的预警传播时序符合匹配预警传播时序的设置阈值时，判断结果为“是”。
进一步地，所述预警通道数量的判断优先级高于预警传播时序。
进一步地，所述刺激模式的匹配优先级依次为预警通道数量的差异、预警传播时序的匹配相似度、传播模式的出现概率。
进一步地，所述刺激模式包括刺激参数；所述刺激参数包括刺激波形的强度、脉宽、频率、电荷密度中的至少一种。
第二方面，本发明提供了一种刺激模式的控制系统，用于运行上述的控制方法，包括：上位机，其用于构建所述特定数据集合；下位机，其用于存储所述特定数据集合，并判断待测生理信号是否属于所述特定数据集合，以选择匹配的刺激模式。
进一步地，所述下位机包括：采集模块、匹配模块、预警模块、判断模块和警示模块；当判断结果为“否”时，所述下位机控制警示模块进行警示；所述上位机包括：数据加载模块、计算模块和设置模块。
第三方面，本发明提供了一种电子设备，包括：处理器和存储器，所述存储器用于存储所述处理器可执行的机器可读指令，当电子设备运行时，所述处理器与所述存储器之间通信连接，所述机器可读指令被所述处理器执行时执行上述的控制方法。
第四方面，本发明提供了一种计算机可读存储介质，该计算机可读存储介质上存储有计算机程序，该计算机程序被处理器运行时执行上述的控制方法。
本发明的有益效果是，本发明的刺激模式的控制方法、控制系统，通过预警算法能够获取多个通道或导联实时的时序数据的预警结果，根据预警结果综合判断是否实施刺激，并选择匹配的刺激模式进行刺激，可以提高刺激的准确率。
附图说明
下面结合附图和实施例对本发明进一步说明。
图1是本发明的刺激模式的控制方法的工作流程图。
图2是本发明的传播矩阵的示意图。
图3是本发明的相似矩阵的聚类结果示意图。
图4是本发明的第一种传播模式的及其出现概率的示意图。
图5是本发明的第二种传播模式的及其出现概率的示意图。
图6是本发明的第三种传播模式的及其出现概率的示意图。
图7是本发明的刺激模式的控制系统的结构示意图。
图8是本发明的聚类算法对肌电信号的处理结果示意图。
图9是本发明的聚类算法对癫痫信号的处理结果示意图。
图10是本发明的肌电信号和癫痫信号的特征对比图。
具体实施方式
现在结合附图对本发明作进一步详细的说明。这些附图均为简化的示意图，仅以示意方式说明本发明的基本结构，因此其仅显示与本发明有关的构成。
在本发明的描述中，需要说明的是，除非另有明确的规定和限定，术语“安装”、“相连”、“连接”应做广义理解，例如，可以是固定连接，也可以是可拆卸连接，或一体地连接；可以是机械连接，也可以是电连接；可以是直接相连，也可以通过中间媒介间接相连，可以是两个元件内部的连通。此外，限定有“第一”、“第二”的特征可以明示或者隐含地包括一个或者更多个该特征。在本发明的描述中，除非另有说明，“多个”的含义是两个或两个以上。对于本领域的普通技术人员而言，可以具体情况理解上述术语在本发明中的具体含义。
在本案中，所述生理信号例如但不限于脑电信号，可以通过控制系统匹配不同的刺激模式，以适应各种神经系统疾病。现以癫痫发病的脑电信号为例， 对本案的刺激模式的控制方法进行具体说明。
癫痫疾病状态一般可以分为发作间期、发作前期、发作期及发作后期这四个状态。发作间期表示患者处于正常状态的脑电信号，发作前期表示患者处于病发之前的一段时间的脑电信号，发作期表示患者处于癫痫发作时的脑电信号，发作后期表示患者癫痫发作之后一段时间的脑电信号。由于发作前期的脑电信号与正常的脑电信号相比会更加活跃，因此，可以利用发作前期的脑电信号来进行癫痫发作预警。
如图1所示，本发明提供了一种刺激模式的控制方法，主要包括以下步骤：构建已测生理信号的特定数据集合；判断待测生理信号是否属于特定数据集合；当判断结果为“是”时，启动刺激并选择匹配的刺激模式；当判断结果为“否”时，进行警示或禁用刺激，当然也可以通过人工操作控制系统选择匹配的刺激模式。
可选的，生理信号采用多个通道检测；特定数据集合包括：已测生理信号的传播模式及其出现概率；其中传播模式包括：生理信号的预警通道数量、预警传播时序中的至少一种。其中刺激模式的控制方法的具体操作过程如下：S1：获取若干个传播模式及每个传播模式出现的概率，形成特定数据集合。S2：选取特定数据集合中的至少一个传播模式并设置一一对应的刺激模式。S3：多个通道同时输出多个预警结果，根据多个预警结果，判断是否启动刺激；若判断结果为“是”，则利用刺激模式对目标对象进行刺激。
需要说明的是，在监测脑电信号时，一般会在目标对象脑部安装多个电极(即多个通道或导联)，多个电极可以分别被布置在目标对象脑部的不同位置进行脑电信号的监测，一个通道对应一个电极。当目标对象处于发作前期时，多个通道监测到的脑电信号变化会按照一定的顺序进行，这个通道数量可以理解 为预警通道数量，这个通道位置的变化顺序可理解为是癫痫传播时序，二者形成癫痫的传播模式。例如，共有5个通道，分别记为通道一、通道二、通道三、通道四和通道五，每个通道分别对应目标对象脑部的不同位置。当目标对象处于癫痫发作前期时，5个通道监测到的脑电信号之间会发生联动。例如，通道一首先监测到发作前期的脑电信号，随着时间推移，通道二、通道三、通道四和通道五再依次监测到发作前期的脑电信号，此时，癫痫传播时序为“通道一→通道二→通道三→通道四→通道五”。当然，癫痫发作传播时序也可以是“通道一→通道三→通道二→通道四→通道五”或者“通道一→通道三→通道四→通道二→通道五”等等。换言之，癫痫的预警通道数量可以反映癫痫发作前期的脑电信号的通道数量；癫痫的预警传播时序可以反映癫痫发作前期的脑电信号变化的通道顺序。将已测的脑电数据发送给上位机，将预警通道数量(即产生预警的通道数量)其出现概率或预警传播时序(即产生预警的传播时序)其出现概率，用于构建特定数据集合。
下面对每个步骤进行具体说明。
步骤S1：获取若干个传播模式及每个传播模式出现的概率，形成特定数据集合。
本步骤获取若干个传播模式及每个传播模式出现的概率可以采用自动获取或者手动获取方式，手动获取例如是将已有的传播模式直接存入上位机中，自动获取例如可以利用目标对象癫痫发作前期的历史数据，通过聚类算法对历史数据进行处理，得到若干个传播模式及每个传播模式出现的概率。其中，历史数据包括多个通道监测的不同位置的脑电数据，聚类算法例如可以是传播矩阵相似度聚类算法，通过聚类算法对历史数据进行处理，具体包括以下步骤。
S11、预处理：对所有通道监测到的历史数据，进行带通滤波处理，筛选出 处于癫痫发作前期的历史数据区间段，再用宽度为t1的滑动窗口，依次取出该历史数据区间段的多个片段，对每个片段做均方根(RMS)处理，使得历史数据的波形更加平滑。
S12、互卷积：卷积是两个变量在某范围内相乘后求和的结果。将多个通道进行两两排列组合，用窗宽为t2，步进为Δt的滑动窗口，分别对两个通道监测得到的数据依次选取数据片段，假设两个通道都能够选取出M个数据片段，分别记为Ma和Mb，将数据片段Ma和Mb之间进行两两卷积运算。例如，Ma1与Mb1、Mb2、Mb3、...Mbj分别进行卷积运算，Ma2与Mb1、Mb2、Mb3、...Mbj分别进行卷积运算，以此类推，Mai与Mb1、Mb2、Mb3、...Mbj分别进行卷积运算，这样两个通道的数据之间进行卷积运算一共可以得到M×M个卷积结果。
S13、链接确认：如果M×M个卷积结果中的最大值大于阈值X，则认为这两个通道之间存在链接关系，否则认为两个通道之间不存在链接关系。
S14、时差计算：获取步骤S13中得到的存在链接关系的多组通道，结合滑动窗次数及步进Δt，计算卷积结果的最大值对应的两个数据片段之间的时差。例如，卷积结果中的最大值是由Ma1和Mb3卷积得到的，但是数据片段Ma1和Mb3对应的时刻是不一样的，因此，需要计算出数据片段Ma1和Mb3之间的时差。
S15、传播矩阵：设通道数目为N，重复步骤S11至S14，可以得到T个N×N维的传播矩阵(如图2所示)，传播矩阵中的数值可以是具体的时差值或者将时差值进行二值化处理后的数值。传播矩阵的横轴表示第j个通道(1≤i≤N)，传播矩阵的纵轴表示第i个通道(1≤j≤N)，传播矩阵中的数值如果是非零值，则表明第j个通道和第i个通道之间存在链接关系，如果传播矩阵中的数值为“1”，则表明第j个通道的传播顺序在第i个通道之前。
S16、传播矩阵相似度：将每个传播矩阵进行矢量化处理，得到传播矩阵对 应的向量，再计算两两向量之间的相似度。相似度的计算方法例如可以采用皮尔森相关系数、欧几里得距离等等，可以根据实际情况进行选择。
S17、相似矩阵：以T个传播矩阵两两之间的相似度作为元素，可以得到一个T×T维的相似矩阵。
S18、相似矩阵聚类：对相似矩阵进行聚类处理，可以得到若干个具有刻板性的传播模式及每个传播模式出现的概率。例如，如图3所示，K1、K2、K3分别表示传播模式一、传播模式二和传播模式三出现的频次。每个传播模式分别代表N个通道的数据之间的联动关系。根据不同传播模式出现的频次，计算每个传播模式出现的概率。如图4至图6所示，传播模式一出现的概率为K1/(K1+K2+K3)，传播模式二出现的概率为K2/(K1+K2+K3)，传播模式三出现的概率为K3/(K1+K2+K3)，并且，每个传播模式对应的起始时间也有所不同，例如，传播模式一对应的起始时间为0-12ms，传播模式二对应的起始时间为0-70ms，传播模式三对应的起始时间为0-7ms，表明每个传播模式出现的时间也是有区别的。
将经过上述步骤获得的若干个传播模式及每个传播模式出现的概率组成特定数据集合，存入上位机中。需要注意的是，用户可以对上位机中保存的传播模式、刺激模式或刺激效果参数进行选择、编辑、新建及保存等操作，如果用户认为上位机中已有的传播模式不符合要求，可以新建或者编辑传播模式，新建或编辑以后，上位机可以自动根据新的传播模式重新计算每个传播模式出现的概率。
步骤S2：选取特定数据集合中的至少一个传播模式并设置相应的刺激模式。
需要说明的是，用户选取上位机中显示的传播模式中的至少一个，并根据选出的传播模式设置相应的刺激模式，例如可以设置刺激波形的强度、脉冲宽 度、频率、电荷密度等参数(即刺激参数)。设置好后需要点击“生效”按钮，使得选出的传播模式及相应的刺激模式传输给下位机或者体内机。
步骤S3：多个通道同时输出多个预警结果，根据多个预警结果，判断是否启动刺激；若判断结果为“是”，则利用刺激模式对目标对象进行刺激。具体的，判断待测生理信号是否属于特定数据集合包括：当待测生理信号的预警通道数量大于或等于预警通道数量的设置阈值时，判断结果为“是”；和/或当待测生理信号的预警传播时序匹配预警传播时序的设置值时，判断结果为“是”。
优选的，预警通道数量的判断优先级高于预警传播时序，即当预警通道数量大于预警通道数量的设置阈值时，判断结果一定为“是”，此时的判断过程不再考量预警传播时序是否匹配。
优选的，刺激模式的匹配优先级依次为预警通道数量的差异、预警传播时序的匹配度、传播模式的出现概率。在选择匹配的刺激模式时，会将癫痫的传播模式与特定数据集合中刺激模式对应的传播模式比较，优先选择预警通道数量的差异最小的刺激模式，其次是预警传播时序的匹配度最高，最后是传播模式的出现概率最大。
需要说明的是，多个通道同时输出多个预警结果，可以采用癫痫预警算法对每个通道采集到的实时时序数据进行癫痫预警判断，输出的预警结果包括启动预警或者不预警。若预警结果为启动预警，则记录对应的预警通道数量及预警传播时序。癫痫预警算法根据实际情况有多种，现列举一种癫痫预警算法的步骤，包括：T1：对多个通道实时采集的脑电原始数据分别进行预处理；T2：计算脑电数据的信号特征；T3：根据信号特征对脑电数据进行分类，输出预警结果。
需要说明的是，步骤T1中的预处理包括降噪、降采样及多窗口划分。多窗 口划分可以采用窗口部分重叠或者不重叠的方式。多窗口划分的目的是每次选取出一个脑电数据的序列片段。步骤T2中的特征信号例如是过零点系数，过零点系数为过零率的映射或过零数的映射；映射为具有正相关或负相关的映射函数；以及映射函数为线性或非线性的。过零点系数能够反映脑电信号的序列片段内的数据值过零点的频次。根据脑电数据的过零点系数，可以区分出正常脑电数据和癫痫发作前期脑电数据。例如，过零点计算公式可以为C＝1-sqrt(num{x(1:N-1).*x(2:N)<0}/(N-1))，N表示待处理的序列片段内有N个点，x(1:N-1)表示序列片段内的前N-1个点的数组，x(2:N)表示序列片段内的后N-1个点的数组，x(1:N-1).*x(2:N)表示两个数组之间进行点对点相乘，num{x(1:N-1).*x(2:N)<0}/(N-1)表示点对点相乘后的结果小于0的概率，即过零率。然后，再通过1-sqrt(n um{x(1:N-1).*x(2:N)<0}/(N-1))处理，将过零率映射为取值范围在0-1之间的过零点系数。在该计算公式下，过零点系数越大，表明脑电数据振荡活跃程度越低，过零点系数越小，表明脑电数据振荡活跃程度越高。计算出每个通道监测到的脑电数据的序列片段的过零点系数，并将每个过零点系数输入已经训练过的分类器中，分类器能够输出每个序列片段的分类结果。例如，分类器输出“1”表示该脑电信号片段为癫痫发作前状态，输出“0”表示该脑电信号片段为正常状态。当一个通道内的脑电数据的序列片段由连续Y个分类结果均为“1”，则认为目标对象处于癫痫发作前，需要启动预警；否则不预警。如果判断结果为启动预警，则需要记录分类结果为“1”的脑电数据对应的时刻(即预警时刻)以及通道序号(即预警通道)。
在本发明中，根据多个预警结果，判断是否启动刺激，具体包括：S31：将预警时刻进行排序得到实际预警传播时序，S32：若预警通道的数量NSZ大于或等于第一阈值N，则直接启动刺激；S32：若预警通道的数量NSZ小于第一阈值 N，则将实际预警传播时序与传播模式进行匹配，若匹配结果为实际预警传播时序是传播模式的子集，再启动刺激。
需要说明的是，将记录下来的多个预警时刻按照升序或者降序进行排序(与传播模式的时序顺序一致即可)，生成实际预警传播时序，同时记录预警通道的数目。如果预警通道的数量NSZ大于或等于第一阈值N，则直接启动刺激，刺激时，采用步骤S2中预设的刺激模式。若预警通道的数量NSZ小于第一阈值N，则将实际预警时序与传播模式进行匹配，如果匹配结果为实际预警传播时序是传播模式的子集，再启动刺激。传播模式实质上也是一段时序，是由多个通道的时刻拼接起来的，当实际预警传播时序是传播模式的子集时，认为也是需要启动刺激的，否则不刺激。例如，传播模式的时序顺序是12345，如果实际预警时序为123或者234等子集，则也是需要启动刺激的。刺激时，采用步骤S2中预设的刺激模式。用户根据刺激效果可以再重复步骤S1至S3。
如图7所示，本发明还提供了一种刺激模式的控制系统，运行上述的刺激模式的控制方法。该系统包括上位机1和下位机2。上位机1(如远程终端、CPU、云服务器)，用于获取、保存及显示特定数据集合，以及设置刺激模式。下位机2(如计算机、处理器)用于存储所述特定数据集合，并判断待测生理信号是否属于特定数据集合，以选择匹配的刺激模式。下位机包括：采集模块21、匹配模块22、预警模块23、判断模块24和警示模块25(如声音提示、禁用刺激控制电路等)；当判断结果为“否”时，下位机2控制警示模块25进行警示；上位机1包括：数据加载模块11、计算模块12和设置模块13。
优选的，本控制系统还可以用于植入体，还包括体内机3，安装于目标对象体内，用于采集多个通道的实时时序数据以及启动刺激。上位机1与体内机3连接，下位机2与体内机3连接。
具体的，采集模块21用于接收体内机3采集到的目标对象的实时时序数据。预警模块23用于接收采集模块21获取的实时时序数据，并对实时时序数据进行癫痫预警算法处理，得到实际预警传播时序及预警通道数目。判断模块24用于判断预警通道数目NSZ是否大于或等于第一阈值N，第一阈值N的大小可以根据实际情况进行设置。匹配模块22用于将实际预警传播时序与传播模式进行匹配，如果匹配结果为实际预警传播时序是传播模式的子集，则将匹配结果发送给体内机3，体内机3对目标对象施加刺激。
具体的，数据加载模块11与计算模块12连接，计算模块12与设置模块13连接；设置模块13与匹配模块32连接。数据加载模块11用于读取、显示历史数据，以及显示通道数目。计算模块12用于计算、显示特定数据集合。上位机1还具有进度条功能，可以查看计算进程，因为计算量比较大时，显示界面可能会卡住，这时如果进度条仍然是在工作的，那么表明整个运算还是在正常进行的，不需要重启运算。设置模块13用于选择传播模式，还可以对传播模式进行编辑、新建和保存等操作，同时可以根据选定的传播模式设置相应的刺激模式，并将选定的传播模式和刺激模式传输给体内机3，体内机3施加刺激时根据预设的刺激模式进行刺激。
实施例
本实施例还可以采用上述控制方法中的聚类算法对患者的癫痫信号和肌电信号分别进行处理，获得图8至图10的结果，以区分癫痫信号和肌电信号，避免造成误判和误刺激。图8是肌电信号的原始波形和经RMS处理后的波形，图9是癫痫信号的原始波形和经RMS处理后的波形。对比这两张图可以发现，肌电信号的传播无时序性，而癫痫信号的传播具有时序性。并且，请参考图10，癫痫信号中具有高链接强度的通道数目少，通道之间的链接强度比较集中，时 差较大；而肌电信号具有高链接强度的通道数目多，通道之间的链接强度比较分散，时差较小。表明采用本方法可以有效区分出癫痫信号和肌电信号，本发明能够有效提高癫痫刺激的准确性，减少误判。
本发明还提供了一种电子设备，包括处理器和存储器，存储器用于存储处理器可执行的机器可读指令，当电子设备运行时，处理器与存储器之间通信连接，机器可读指令被处理器执行时执行上述的刺激模式的控制方法的步骤。
本发明还提供了一种计算机可读存储介质，该计算机可读存储介质上存储有计算机程序，该计算机程序被处理器运行时执行上述的刺激模式的控制方法的步骤。实际应用中，计算机可读介质可以是上述系统中所包含的，也可以是单独存在的。计算机可读存储介质承载有一个或者多个程序，当一个或多个程序被执行时，实现所描述的分析方法。计算机可读存储介质可以是非易失性的计算机可读存储介质，例如可以包括但不限于：便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、便携式紧凑磁盘只读存储器(CDROM)、光存储器件、磁存储器件，或者上述的任意合适的组合，但不用于限制本申请保护的范围。
综上，本发明的刺激模式的控制方法、控制系统，结合已测生理信号的传播模式及预警算法，构建已测生理信号的特定数据集合，然后判断待测生理信号是否属于特定数据集合；当判断结果为“是”时，启动刺激并选择匹配的刺激模式，实现了刺激模式的有效调控，避免了无效刺激及其产生的副作用，可以大幅提高刺激的准确率和安全性。此外，本发明还能够有效区分出癫痫信号和肌电信号，提升癫痫预警的准确率和癫痫刺激的准确率，减少误判，具有很高的应用价值。
以上述依据本发明的理想实施例为启示，通过上述的说明内容，相关工作 人员完全可以在不偏离本项发明技术思想的范围内，进行多样的变更以及修改。本项发明的技术性范围并不局限于说明书上的内容，必须要如权利要求范围来确定其技术性范围。

Claims (10)

  1. 一种刺激模式的控制方法，其特征在于，包括：
    构建已测生理信号的特定数据集合；
    判断待测生理信号是否属于所述特定数据集合；
    当判断结果为“是”时，启动刺激并选择匹配的刺激模式。
  2. 如权利要求1所述的控制方法，其特征在于，
    所述生理信号采用多个通道检测；
    所述特定数据集合包括：已测生理信号的传播模式及其出现概率；其中
    所述传播模式包括：生理信号的预警通道数量、预警传播时序中的至少一种。
  3. 如权利要求2所述的控制方法，其特征在于，
    所述判断待测生理信号是否属于所述特定数据集合包括：
    当待测生理信号的预警通道数量大于或等于预警通道数量的设置阈值时，判断结果为“是”；和/或
    当待测生理信号的预警传播时序匹配预警传播时序的设置值时，判断结果为“是”。
  4. 如权利要求3所述的控制方法，其特征在于，
    所述预警通道数量的判断优先级高于预警传播时序。
  5. 如权利要求2所述的控制方法，其特征在于，
    所述刺激模式的匹配优先级依次为预警通道数量的差异、预警传播时序的匹配度、传播模式的出现概率。
  6. 如权利要求1所述的控制方法，其特征在于，
    所述刺激模式包括刺激参数；
    所述刺激参数包括刺激波形的强度、脉宽、频率、电荷密度中的至少一种。
  7. 一种刺激模式的控制系统，其特征在于，用于运行如权利要求1所述的控制方法，其特征在于，包括：
    上位机，其用于构建所述特定数据集合；
    下位机，其用于存储所述特定数据集合，并判断待测生理信号是否属于所述特定数据集合，以选择匹配的刺激模式。
  8. 如权利要求7所述的控制系统，其特征在于，
    所述下位机包括：采集模块、匹配模块、预警模块、判断模块和警示模块；
    当判断结果为“否”时，所述下位机控制警示模块进行警示；
    所述上位机包括：数据加载模块、计算模块和设置模块。
  9. 一种电子设备，其特征在于，包括：处理器和存储器，所述存储器用于存储所述处理器可执行的机器可读指令，当电子设备运行时，所述处理器与所述存储器之间通信连接，所述机器可读指令被所述处理器执行时执行如权利要求1至6任一所述的控制方法。
  10. 一种计算机可读存储介质，其特征在于，该计算机可读存储介质上存储有计算机程序，该计算机程序被处理器运行时执行如权利要求1至6任一所述的控制方法。
PCT/CN2023/071875 2022-01-13 2023-01-12 刺激模式的控制方法、控制系统、电子设备及介质 WO2023134720A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210037062.4 2022-01-13
CN202210037062.4A CN114470516A (zh) 2022-01-13 2022-01-13 刺激模式的控制方法、控制系统、电子设备及介质

Publications (1)

Publication Number Publication Date
WO2023134720A1 true WO2023134720A1 (zh) 2023-07-20

Family

ID=81510958

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/071875 WO2023134720A1 (zh) 2022-01-13 2023-01-12 刺激模式的控制方法、控制系统、电子设备及介质

Country Status (2)

Country Link
CN (1) CN114470516A (zh)
WO (1) WO2023134720A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117100291A (zh) * 2023-10-18 2023-11-24 杭州般意科技有限公司 一种经颅直流电刺激设备的干预刺激模式的评价方法
CN118356202A (zh) * 2024-06-20 2024-07-19 博睿康医疗科技(上海)有限公司 基于任务获取电刺激序列的皮质间诱发电的电刺激设备

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114470516A (zh) * 2022-01-13 2022-05-13 博睿康医疗科技(上海)有限公司 刺激模式的控制方法、控制系统、电子设备及介质
CN115878969B (zh) * 2023-02-06 2023-05-26 博睿康科技（常州）股份有限公司 基于离线检测结果的刺激系统的调参方法、分时刺激系统

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160228705A1 (en) * 2015-02-10 2016-08-11 Neuropace, Inc. Seizure onset classification and stimulation parameter selection
CN109646796A (zh) * 2019-01-17 2019-04-19 浙江大学 用于癫痫治疗的多通道无线闭环神经电刺激系统
US20190160287A1 (en) * 2017-11-30 2019-05-30 International Business Machines Corporation Seizure detection, prediction and prevention using neurostimulation technology and deep neural network
CN111346297A (zh) * 2020-03-16 2020-06-30 首都医科大学宣武医院 多靶点电刺激电路、电刺激器及其信号输出方法
US10743809B1 (en) * 2019-09-20 2020-08-18 CeriBell, Inc. Systems and methods for seizure prediction and detection
US20210282701A1 (en) * 2020-03-16 2021-09-16 nCefalon Corporation Method of early detection of epileptic seizures through scalp eeg monitoring
CN114470516A (zh) * 2022-01-13 2022-05-13 博睿康医疗科技(上海)有限公司 刺激模式的控制方法、控制系统、电子设备及介质

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160228705A1 (en) * 2015-02-10 2016-08-11 Neuropace, Inc. Seizure onset classification and stimulation parameter selection
US20190160287A1 (en) * 2017-11-30 2019-05-30 International Business Machines Corporation Seizure detection, prediction and prevention using neurostimulation technology and deep neural network
CN109646796A (zh) * 2019-01-17 2019-04-19 浙江大学 用于癫痫治疗的多通道无线闭环神经电刺激系统
US10743809B1 (en) * 2019-09-20 2020-08-18 CeriBell, Inc. Systems and methods for seizure prediction and detection
CN111346297A (zh) * 2020-03-16 2020-06-30 首都医科大学宣武医院 多靶点电刺激电路、电刺激器及其信号输出方法
US20210282701A1 (en) * 2020-03-16 2021-09-16 nCefalon Corporation Method of early detection of epileptic seizures through scalp eeg monitoring
CN114470516A (zh) * 2022-01-13 2022-05-13 博睿康医疗科技(上海)有限公司 刺激模式的控制方法、控制系统、电子设备及介质

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117100291A (zh) * 2023-10-18 2023-11-24 杭州般意科技有限公司 一种经颅直流电刺激设备的干预刺激模式的评价方法
CN117100291B (zh) * 2023-10-18 2024-01-30 深圳般意科技有限公司 一种经颅直流电刺激设备的干预刺激模式的评价方法
CN118356202A (zh) * 2024-06-20 2024-07-19 博睿康医疗科技(上海)有限公司 基于任务获取电刺激序列的皮质间诱发电的电刺激设备

Also Published As

Publication number Publication date
CN114470516A (zh) 2022-05-13

Similar Documents

Publication Publication Date Title
WO2023134720A1 (zh) 刺激模式的控制方法、控制系统、电子设备及介质
US20210236819A1 (en) System and apparatus for increasing regularity and/or phase-locking of neuronal activity relating to an epileptic event
US20200253559A1 (en) Apparatus and systems for event detection using probabilistic measures
US10835131B2 (en) Seizure detection methods, apparatus, and systems using a wavelet transform maximum modulus algorithm
WO2023130600A1 (zh) 基于过零点系数的时域数据分类方法、植入式刺激系统
US5995868A (en) System for the prediction, rapid detection, warning, prevention, or control of changes in activity states in the brain of a subject
US9037223B2 (en) Atrial fibrillation classification using power measurement
US10820816B2 (en) System for a brain-computer interface
US12048567B2 (en) System, method, and computer algorithm for measuring, displaying, and accurately detecting changes in electrophysiological evoked potentials
WO2010123542A2 (en) Methods and systems for detecting epileptic events using nonlinear analysis parameters
EP2765906A1 (en) Apparatus and systems for event detection using probabilistic measures
CN106943150A (zh) 精神疲劳检测系统及其采用的方法
CN110720900A (zh) 一种脑状态监测与调控装置、方法、处理器及终端设备
Vicnesh et al. Accurate detection of seizure using nonlinear parameters extracted from EEG signals
CN116492596B (zh) 脉冲发生器、刺激器及存储介质
Bhavaraju et al. Analog seizure detection and performance evaluation
CN117065217A (zh) 电位信号采集设备及其方法、医疗系统、可读存储介质
Basu et al. Adaptive control of deep brain stimulator for essential tremor: entropy-based tremor prediction using surface-EMG
CN203524665U (zh) 脊髓监护仪
CN113112017B (zh) 基于神经流形的脑电分级与预后fpga解码系统
US20200237244A1 (en) Signal replay for selection of optimal detection settings
CN204745287U (zh) 一种基于心率变异性的催眠治疗抑郁症效果评价系统
Heller et al. Microwatt power hardware implementation of machine learning algorithms on MSP430 microcontrollers
CN117379002A (zh) 癫痫在线反馈神经调控系统及设备
Tribhuvanam et al. ECG Abnormality Classification and Analysis with SVM Classifier

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23740062

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE