Acupuncture treatment effect real-time evaluation system based on brain-computer interface technology

Abstract

The invention discloses an acupuncture treatment effect real-time evaluation system based on a brain-computer interface technology, and belongs to the technical field of acupuncture treatment effect evaluation, and the acupuncture treatment effect real-time evaluation system comprises a brain-computer data collection module, an acupuncture data acquisition module, a treatment effect real-time evaluation module, a patient portrait generation module and a long-time treatment effect comprehensive evaluation module, comprising an electroencephalogram sensor which collects electroencephalogram signals of a patient before treatment and in the treatment process based on a non-invasive brain-computer interface technology and transmits the electroencephalogram signals to a follow-up module, and the acupuncture data acquisition module comprises a high-definition camera which is used for collecting actions of a doctor in the treatment process and judging acupuncture points and acupuncture depth of the current patient in the treatment process. According to the acupuncture and moxibustion treatment effect real-time evaluation system based on the brain-computer interface technology, by combining the brain-computer interface technology and acupuncture and moxibustion treatment characteristics, an acupuncture and moxibustion effect real-time evaluation scheme is established based on individual differences of patients, so that the accuracy and effectiveness of acupuncture and moxibustion treatment are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of acupuncture efficacy evaluation, and specifically is a real-time evaluation system for acupuncture treatment effects based on brain-computer interface technology. Background Art

[0002] Acupuncture is a traditional treatment method originated from China. It is an important part of traditional Chinese medicine. Acupuncture includes two methods: "needle" and "moxibustion". "Needle" refers to the use of special needles to pierce certain acupuncture points on the human body to treat diseases, while "moxibustion" refers to the use of moxa or other flammable materials to burn specific parts of the body surface to achieve the purpose of treatment through warm stimulation. Modern acupuncture usually focuses on acupuncture. Due to individual differences among patients, during acupuncture, the techniques and depths of acupuncture will vary among different patients. Different techniques and depths of acupuncture will also have different therapeutic effects on different patients. The existing real-time evaluation system for acupuncture treatment effect is difficult to evaluate the acupuncture efficacy in the treatment process in real time based on individual differences. It is also impossible to evaluate the differences among individual patients based on different techniques and depths of acupuncture, and has problems of low practicality and functionality. In response to the above, this case proposes a real-time evaluation system for acupuncture treatment effects based on brain-computer interface technology to solve the above technical problems. Summary of the invention

[0003] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a real-time evaluation system for acupuncture treatment effect based on brain-computer interface technology, which solves the above technical problems by improving the detection method and processing method.

[0004] In order to achieve the above object, the present invention adopts the following technical solutions: A real-time evaluation system for acupuncture treatment effect based on brain-computer interface technology, including a brain-computer data collection module, an acupuncture data acquisition module, a real-time efficacy evaluation module, a patient portrait generation module, and a long-term efficacy comprehensive evaluation module; The brain-computer data collection module includes an EEG sensor, which collects the patient's EEG signals before and during treatment based on non-embedded brain-computer interface technology and transmits them to subsequent modules; The acupuncture data acquisition module includes a high-definition camera to collect the doctor's actions during the treatment process, to determine the acupuncture points, acupuncture depth and acupuncture techniques during the current patient treatment process, and to transmit relevant data to subsequent modules; The real-time efficacy evaluation module collects EEG signal data of different patients during treatment under the current condition based on historical diagnosis and treatment data, determines the parameters affecting the treatment effect, and evaluates the treatment effect of the patient in real time based on the changes in EEG signals of the current patient during treatment; The patient portrait generation module generates a treatment portrait of the patient based on the doctor's acupuncture technique and acupuncture depth during acupuncture treatment, and associates the current patient's treatment feedback EEG signal to generate the patient's treatment sensitivity and treatment effect improvement, and comprehensively determine the best treatment plan; The long-term efficacy comprehensive evaluation module sets long-term efficacy evaluation nodes based on the patient's treatment cycle, and conducts long-term efficacy evaluation on patients in the current cycle in combination with the patient-specific efficacy evaluation scores within the cycle.

[0005] Furthermore, the acupuncture data acquisition module includes a high-definition camera to collect the doctor's actions during the treatment process, to determine the acupuncture points, acupuncture depth and acupuncture techniques during the current patient treatment process, and to transmit relevant data to subsequent modules, including the following steps: The doctor's acupuncture movements are captured by a high-definition camera, and the video stream of the treatment process is collected. The body parts in the video stream are identified by the target detection algorithm, and the characteristic parameters of the acupuncture parts are recorded. The acupuncture points of the current patient are determined by cosine similarity comparison. Extract the initial length of the needle in the video stream through the target detection algorithm , combined with the remaining length of the needle after acupuncture Calculate the acupuncture depth ; Regarding acupuncture techniques, high-definition video data of different doctors performing various acupuncture techniques are collected, and key features of acupuncture hand movements are extracted, including movement type, movement direction, and movement amplitude. Training sets and test sets are established for different acupuncture techniques, and the acupuncture technique model is trained through convolutional neural networks. The acupuncture feature data in the current video stream is substituted frame by frame into the trained neural network acupuncture technique model, and the degree of matching between the current frame and each known technique model is calculated. The acupuncture technique is determined based on the similarity value.

[0006] Furthermore, the real-time efficacy evaluation module collects EEG signal data of different patients during treatment under the current condition based on historical diagnosis and treatment data, determines the parameters affecting the treatment effect, and evaluates the treatment effect of the patient in real time in combination with the changes in EEG signals during the current patient's treatment. The specific steps are as follows: Collect historical patient diagnosis and treatment data of the same disease, combine the EEG signal data of different patients during the treatment of the current disease, divide the EEG signal bands, and distinguish between positive and negative EEG signal bands, determine the parameters affecting the treatment effect, and combine the EEG signal changes of the current patient during the treatment process to evaluate the patient's treatment effect in real time. The specific steps are as follows: According to the frequency range of EEG signal fluctuations of patients collected during historical treatment, the EEG signals are divided into different frequency bands. The collected EEG signals are converted from the time domain to the frequency domain through fast Fourier transform, the power spectrum density of each frequency component is calculated, and the signal characteristics of different frequency bands are determined; Based on the historical disease diagnosis and treatment data set and the current patient treatment feedback and symptom changes, the association between different frequency bands and treatment effects is determined, that is, the fluctuation frequency bands when the patient's symptoms are relieved and the fluctuation frequency bands when the patient's pain is aggravated or the symptoms are worsened are recorded, and the former are divided into positive EEG signal bands, and the latter are divided into negative EEG signal bands; According to the initial power spectral density of each frequency band of the patient before treatment, combined with the power spectral density of each frequency band after the treatment is completed, the fluctuation values ​​of different frequency bands in the positive frequency band and the fluctuation values ​​of different frequency bands in the negative frequency band are obtained. By multiplying the fluctuation value of the frequency band with the weight coefficient corresponding to the frequency band, accumulating the products of each frequency band in the positive frequency band, accumulating each product in the negative frequency band, and finally summing the accumulated values ​​of the positive frequency band and the accumulated values ​​of the negative frequency band, the real-time efficacy evaluation score during the treatment is obtained. When the real-time efficacy evaluation score is greater than 0, it means that the treatment has a positive effect. When the real-time efficacy evaluation score is less than 0, it means that the treatment has a negative effect.

[0007] Furthermore, the patient portrait generation module generates a treatment portrait of the patient based on the doctor's acupuncture technique and acupuncture depth during acupuncture treatment, and associates the current patient's treatment feedback EEG signal to generate the patient's treatment sensitivity and treatment effect improvement, and comprehensively determines the best treatment plan. The specific steps are: Establish a timestamp based on the changes in the EEG signals during the patient's treatment process, and simultaneously establish a timestamp for the acupuncture data during the patient's treatment process, and associate the acupuncture data and brain-computer data during the current patient's treatment process; Based on the division results of feedback EEG signals in the real-time efficacy evaluation module, positive feedback EEG signal data and negative feedback EEG signal data are obtained. Combined with the correlation between relevant feedback EEG signal data and acupuncture data, the patient's treatment portrait is generated, including the treatment sensitivity of different acupuncture data to the patient and the degree of improvement in treatment effect, and the best treatment plan is comprehensively determined.

[0008] Furthermore, the timestamp is established based on the changes in the EEG signals during the patient's treatment process, and the acupuncture data during the patient's treatment process is synchronously timestamped, and the acupuncture data and brain-computer data during the current patient's treatment process are associated. The specific steps are: Based on different acupuncture techniques, the corresponding timestamps of acupuncture depth and different EEG signal frequency band fluctuations under the corresponding acupuncture techniques are established, and the EEG signal frequency bands that are positively or negatively correlated with the acupuncture depth under the corresponding acupuncture techniques are calculated. The specific steps are: In the EEG signal data, the acupuncture technique and acupuncture depth corresponding to each time point are marked, and the power spectrum density of the specific frequency band of the EEG signal fluctuation is matched according to the timestamp. The correlation between the acupuncture depth under the current acupuncture technique and the corresponding EEG signal characteristic fluctuation is calculated by the Pearson correlation coefficient: The Pearson correlation coefficient between the acupuncture depth and the power spectral density fluctuation of different EEG signal specific frequency bands under the current acupuncture technique is calculated respectively. The specific algorithm formula is: ; in, Represents the depth of acupuncture under acupuncture technique Q, represents the power spectrum density value of EEG signal fluctuation in frequency band a, Represents the Pearson correlation coefficient of the acupuncture depth under acupuncture manipulation Q and the power spectrum density value of the EEG signal fluctuation under frequency band a; in, The value range is from -1 to 1. When <0, it means that the depth of needle y under acupuncture technique Q is negatively correlated with the frequency band a, that is, when one variable increases, the other variable decreases; when When ≈0, it means that the needle depth y under acupuncture technique Q is unrelated to the frequency band a, that is, when one variable increases or decreases, the other variable does not change; when When >0, it means that the needle depth y under acupuncture technique Q is positively correlated with the frequency band a, that is, when one variable increases, the other variable increases.

[0009] Furthermore, the feedback EEG signal division result in the real-time efficacy evaluation module is used to obtain positive feedback EEG signal data and negative feedback EEG signal data, and the correlation between the relevant feedback EEG signal data and acupuncture data is combined to generate a treatment portrait of the patient, including the treatment sensitivity of different acupuncture data to the patient and the degree of improvement of the treatment effect, and comprehensively determine the best treatment plan. The specific steps are: The frequency band a that is correlated with the needling depth y under the same acupuncture technique Q is counted, and a patient acupuncture database is established through MySQL. A patient portrait file is established in the database and the file is subdivided based on the type of acupuncture technique Q. In each acupuncture technique Q file, files for shallow, medium, and deep needling depths are established respectively. In the files for shallow, medium, and deep needling depths, positively correlated frequency bands, negatively correlated frequency bands, and irrelevant frequency bands are established. In each positively correlated frequency band, negatively correlated frequency band, and irrelevant frequency band file, positive frequency band files and negative frequency band files are established respectively. The frequency bands divided according to the Pearson correlation coefficient are summarized into each positively correlated frequency band, negatively correlated frequency band, and irrelevant frequency band file in combination with the acupuncture depth. The frequency bands are further divided into positive frequency band files and negative frequency band files in combination with the frequency band attributes divided by the real-time efficacy evaluation module. The acupuncture sensitivity and treatment improvement degree under different acupuncture techniques Q and different needle depths are calculated respectively. The specific steps are as follows: For acupuncture sensitivity, the Pearson correlation coefficients of all negative frequency bands extracted from the negative correlation frequency bands under the current acupuncture technique Q were calculated. , calculate the effect size of the negatively correlated frequency band , and its algorithm formula is: ; in, is the number of negative bands in the negative correlation band file, is the negative correlation coefficient of the negative frequency band, It is the product of the absolute value of the negative correlation coefficient and the number of negative frequency bands; Statistically extract the Pearson correlation coefficient of all negative frequency bands from the positive correlation frequency bands under the current acupuncture technique Q , calculate the effect size of the positive correlation band , and its algorithm formula is: ; in, is the number of negative bands in the positive correlation band file, is the positive correlation coefficient of the negative frequency band, is the product of the absolute value of the positive correlation coefficient and the number of negative frequency bands. and Obtaining the patient's acupuncture sensitivity ,in , The larger the value, the greater the acupuncture sensitivity of the current treatment. ; In terms of the improvement of treatment effect, the Pearson correlation coefficients of all positive frequency bands extracted from the negative correlation frequency bands under the current acupuncture technique Q are calculated. , calculate the effect size of the negatively correlated frequency band , and its algorithm formula is: ; in, is the number of positive bands in the negatively correlated band profile, is the negative correlation coefficient of the positive band, It is the product of the absolute value of the negative correlation coefficient and the number of positive frequency bands; Statistically extract the Pearson correlation coefficient of all positive frequency bands in the positive correlation frequency band under the current acupuncture technique Q , calculate the effect size of the positive correlation band , and its algorithm formula is: ; in, is the number of positive bands in the positive correlation band file, is the positive correlation coefficient of the positive frequency band, is the product of the absolute value of the positive correlation coefficient and the number of positive frequency bands. and Obtaining the patient's acupuncture sensitivity ,in , The larger the value, the greater the improvement of the therapeutic effect of the current treatment. The values ​​of ; Calculate the comprehensive impact of different acupuncture depths ,when >0 means the treatment effect is positive. <0 means negative treatment effect. >0, and the acupuncture techniques and acupuncture depths ranked first are selected as the specific treatment plan for the current patient, and the different acupuncture depths under different acupuncture techniques are recorded in the patient portrait file. value.

[0010] Furthermore, the real-time efficacy evaluation module also includes generating a specific efficacy evaluation score for the current patient's treatment based on the patient portrait file established in the patient portrait generation module during the current patient's treatment process, combined with the acupuncture technique and acupuncture depth during the current patient's treatment process; Through the acupuncture data collection module, the acupuncture technique and acupuncture depth of each acupuncture treatment process are obtained, and the comprehensive impact of different acupuncture techniques and different acupuncture depths of different patients are obtained based on the current patient portrait file. , calculate the patient's treatment-specific efficacy evaluation score, and the algorithm formula is: ; in, represents the patient's specific efficacy evaluation score for this treatment, and i represents the number of acupuncture treatments for the patient.

[0011] Furthermore, the long-term efficacy comprehensive evaluation module sets a long-term efficacy evaluation node based on the patient's treatment cycle, and performs a long-term efficacy evaluation on the patients in the current cycle in combination with the patient-specific efficacy evaluation score in the cycle. The specific steps are as follows: Based on the number of treatments n in the current patient's treatment cycle, the long-term efficacy evaluation node is set based on the interval number T, and the patient's treatment cycle is divided into In each stage, the time of each treatment in the current stage is counted separately. After the patient's treatment period is over, the The values ​​are recorded and a line graph is drawn.

[0012] Furthermore, the brain-computer data collection module includes an EEG sensor, which collects the patient's EEG signals before and during treatment based on non-invasive brain-computer interface technology and transmits them to subsequent modules. The specific steps are as follows: Select appropriate EEG sensors, including non-invasive dry electrodes and wet electrodes, to be placed on the patient's forehead and scalp area. Use non-invasive brain-computer interface technology to capture the patient's EEG signal frequency bands before and during treatment, and add a timestamp to each EEG signal sample.

[0013] Compared with the prior art, the present invention has the following beneficial effects: In the present invention, by setting up a patient portrait generation module, according to the individual differences of different patients, the effects of acupuncture depth of different patients under different acupuncture techniques are statistically collected and collected respectively, and the acupuncture sensitivity and treatment effect improvement of different patients are obtained through the negative frequency bands of different patients recorded in the archives, so as to evaluate the acupuncture effect of patients in a targeted manner, thereby enhancing the targetedness of the system; In the present invention, the comprehensive influence of different acupuncture techniques and needle depths on the patient is calculated, so as to assist the doctor in adopting the best acupuncture plan to treat the patient according to the current patient's condition, provide objective indicator support for the effect of acupuncture treatment, facilitate real-time optimization of the patient's treatment plan during acupuncture treatment, and enhance the practicality of the system; In the present invention, through the real-time efficacy evaluation module, combined with non-invasive brain-computer technology, the therapeutic effect of the patient can be evaluated in real time during the acupuncture treatment process, which can timely detect the discomfort or adverse reactions of the patient during the treatment process to avoid excessive stimulation. At the same time, real-time data can help doctors optimize acupuncture treatment parameters including acupuncture depth and acupuncture techniques, thereby enhancing the functionality of the system. In the present invention, by performing specific treatment effect evaluation on individual patients, dividing the treatment stages in combination with the treatment cycle, and statistically calculating the specific treatment effect evaluation score at each treatment stage and drawing a line graph, the specific treatment response of each patient is carefully understood, and by statistically calculating the evaluation score at each treatment stage, the treatment progress is monitored in real time, and the treatment strategy is adjusted in time to improve the treatment effect; The entire real-time evaluation system for acupuncture treatment effects based on brain-computer interface technology combines brain-computer interface technology with the characteristics of acupuncture treatment, and establishes a real-time evaluation plan for acupuncture effects based on individual differences of patients to improve the accuracy and effectiveness of acupuncture treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 This is a block diagram of a real-time evaluation system for acupuncture treatment effects based on brain-computer interface technology of the present invention. DETAILED DESCRIPTION

[0015] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0016] Embodiment 1, as Figure 1 As shown, a real-time evaluation system for acupuncture treatment effect based on brain-computer interface technology includes a brain-computer data collection module, an acupuncture data collection module, a real-time efficacy evaluation module, a patient portrait generation module, and a long-term efficacy comprehensive evaluation module; The brain-computer data collection module, including the EEG sensor, collects the patient's EEG signals before and during treatment based on the non-embedded brain-computer interface technology, and transmits them to the subsequent modules. The specific steps are as follows: Select appropriate EEG sensors, including non-invasive dry electrodes and wet electrodes, to be placed on the patient's forehead and scalp area, and use non-invasive brain-computer interface technology to capture the patient's EEG signal frequency bands before and during treatment, and add a timestamp to each EEG signal sample; The acupuncture data acquisition module includes a high-definition camera to collect the doctor's actions during the treatment process, to determine the acupuncture points, acupuncture depth and acupuncture techniques during the current patient's treatment process, and to transmit relevant data to subsequent modules, including the following steps: The doctor's acupuncture movements are captured by a high-definition camera, and the video stream of the treatment process is collected. The body parts in the video stream are identified by the target detection algorithm, and the characteristic parameters of the acupuncture parts are recorded. The acupuncture points of the current patient are determined by cosine similarity comparison. Extract the initial length of the needle in the video stream through the target detection algorithm , combined with the remaining length of the needle after acupuncture Calculate the acupuncture depth ; Regarding acupuncture techniques, high-definition video data of different doctors performing various acupuncture techniques are collected, and key features of acupuncture hand movements are extracted, including movement type, movement direction, and movement amplitude. Training sets and test sets are established for different acupuncture techniques, and the acupuncture technique model is trained through convolutional neural networks. The acupuncture feature data in the current video stream is substituted frame by frame into the trained neural network acupuncture technique model, and the degree of matching between the current frame and each known technique model is calculated. The acupuncture technique is determined based on the similarity value.

[0017] It should be noted that in the process of extracting key features of acupuncture hand movements, experienced acupuncture experts are needed to annotate the key features of hand movements frame by frame. Acupuncture techniques include lifting and inserting, tonifying and draining, twisting and draining, and flat tonifying and draining. Action types include lifting and inserting, twisting, etc. Feature models of different acupuncture techniques are established through convolutional neural networks. The feature model is combined with the input features to calculate the degree of match between the current frame and each known technique feature model. The current acupuncture technique is judged based on the similarity threshold. That is, when the similarity between the current acupuncture technique and each feature model is greater than the similarity threshold of a certain feature model, it means that the current acupuncture technique is the acupuncture technique represented by the feature model.

[0018] The real-time efficacy evaluation module collects EEG signal data of different patients during the treatment of the current disease based on historical diagnosis and treatment data, determines the parameters affecting the treatment effect, and combines the changes in EEG signals of the current patient during the treatment to evaluate the treatment effect of the patient in real time. The specific steps are as follows: Collect historical patient diagnosis and treatment data of the same disease, combine the EEG signal data of different patients during the treatment of the current disease, divide the EEG signal bands, and distinguish between positive and negative EEG signal bands, determine the parameters affecting the treatment effect, and combine the EEG signal changes of the current patient during the treatment process to evaluate the patient's treatment effect in real time. The specific steps are as follows: According to the frequency range of EEG signal fluctuations of patients collected during historical treatment, the EEG signals are divided into different frequency bands. The collected EEG signals are converted from the time domain to the frequency domain through fast Fourier transform, the power spectrum density of each frequency component is calculated, and the signal characteristics of different frequency bands are determined; Based on the historical disease diagnosis and treatment data set and the current patient treatment feedback and symptom changes, the association between different frequency bands and treatment effects is determined, that is, the fluctuation frequency bands when the patient's symptoms are relieved and the fluctuation frequency bands when the patient's pain is aggravated or the symptoms are worsened are recorded, and the former are divided into positive EEG signal bands, and the latter are divided into negative EEG signal bands; According to the initial power spectral density of each frequency band of the patient before treatment, combined with the power spectral density of each frequency band after the treatment is completed, the fluctuation values ​​of different frequency bands in the positive frequency band and the fluctuation values ​​of different frequency bands in the negative frequency band are obtained. By multiplying the fluctuation value of the frequency band with the weight coefficient corresponding to the frequency band, accumulating the products of each frequency band in the positive frequency band, accumulating each product in the negative frequency band, and finally summing the accumulated values ​​of the positive frequency band and the accumulated values ​​of the negative frequency band, the real-time efficacy evaluation score during the treatment is obtained. When the real-time efficacy evaluation score is greater than 0, it means that the treatment has a positive effect. When the real-time efficacy evaluation score is less than 0, it means that the treatment has a negative effect.

[0019] It should be noted that the weight coefficients of each frequency band in the positive frequency band and the weight coefficients of each frequency band in the negative frequency band need to be set according to the treatment results represented by different frequency bands in the historical data and the experience of experts in related fields. The fluctuation value includes positive and negative values, so the accumulated values ​​of the positive frequency band and the accumulated values ​​of the negative frequency band also include positive and negative values. The fluctuation value is the real-time power spectral density value of the relevant frequency band during the treatment process minus the initial power spectral density value of the frequency band.

[0020] Embodiment 2, a patient portrait generation module, based on the doctor's acupuncture technique and acupuncture depth during acupuncture treatment, associates the current patient's treatment feedback EEG signal, generates the patient's treatment portrait, including the patient's treatment sensitivity and treatment effect improvement, and comprehensively determines the best treatment plan. The specific steps are: A timestamp is established based on the changes in the EEG signals during the patient's treatment process. At the same time, a timestamp is synchronously established for the acupuncture data during the patient's treatment process. The acupuncture data and brain-computer data during the current patient's treatment process are associated. The specific steps are as follows: Based on different acupuncture techniques, the corresponding timestamps of acupuncture depth and different EEG signal frequency band fluctuations under the corresponding acupuncture techniques are established, and the EEG signal frequency bands that are positively or negatively correlated with the acupuncture depth under the corresponding acupuncture techniques are calculated. The specific steps are: In the EEG signal data, the acupuncture technique and acupuncture depth corresponding to each time point are marked, and the power spectrum density of the specific frequency band of the EEG signal fluctuation is matched according to the timestamp. The correlation between the acupuncture depth under the current acupuncture technique and the corresponding EEG signal characteristic fluctuation is calculated by the Pearson correlation coefficient: The Pearson correlation coefficient between the acupuncture depth and the power spectral density fluctuation of different EEG signal specific frequency bands under the current acupuncture technique is calculated respectively. The specific algorithm formula is: ; in, Represents the depth of acupuncture under acupuncture technique Q, represents the power spectrum density value of EEG signal fluctuation in frequency band a, Represents the Pearson correlation coefficient of the acupuncture depth under acupuncture manipulation Q and the power spectrum density value of the EEG signal fluctuation under frequency band a; It should be noted that the acupuncture technique Q is the acupuncture technique in the acupuncture technique model trained by the acupuncture data acquisition module, including the lifting and inserting method, the twisting method, the flat supplementation and drainage method, etc. The frequency band a is the treatment effect influencing parameter determined by the real-time efficacy evaluation module based on historical diagnosis and treatment data. The frequency band is divided into positive frequency bands and negative frequency bands. By calculating the impact of the acupuncture depth on the frequency band under the same acupuncture technique, the impact of different acupuncture techniques and needle depths on different EEG signal frequency bands can be determined, assisting doctors in adjusting the acupuncture treatment plan.

[0021] in, The value range is from -1 to 1. When <0, it means that the depth of needle y under acupuncture technique Q is negatively correlated with the frequency band a, that is, when one variable increases, the other variable decreases; when When ≈0, it means that the needle depth y under acupuncture technique Q is unrelated to the frequency band a, that is, when one variable increases or decreases, the other variable does not change; when When >0, it means that the needle depth y under acupuncture technique Q is positively correlated with the frequency band a, that is, when one variable increases, the other variable increases.

[0022] It should be noted that The value range is from -1 to 1, that is, when The closer it is to 1, the stronger the positive correlation between the two variables. The closer it is to -1, the stronger the negative correlation between the two variables. The closer it is to 0, the weaker the correlation between the two variables. When <0, it means that when the acupuncture depth increases, the power spectrum density of the corresponding EEG signal will decrease. When it is greater than 0, it means that when the acupuncture depth increases, the power spectrum density of the corresponding EEG signal will increase.

[0023] Based on the division results of feedback EEG signals in the real-time efficacy evaluation module, positive feedback EEG signal data and negative feedback EEG signal data are obtained. Combined with the correlation between relevant feedback EEG signal data and acupuncture data, a treatment portrait of the patient is generated, including the treatment sensitivity of different acupuncture data to the patient and the degree of improvement in treatment effect. The best treatment plan is determined comprehensively. The specific steps are as follows: The frequency band a that is correlated with the needling depth y under the same acupuncture technique Q is counted, and a patient acupuncture database is established through MySQL. A patient portrait file is established in the database and the file is subdivided based on the type of acupuncture technique Q. In each acupuncture technique Q file, files for shallow, medium, and deep needling depths are established respectively. In the files for shallow, medium, and deep needling depths, positively correlated frequency bands, negatively correlated frequency bands, and irrelevant frequency bands are established. In each positively correlated frequency band, negatively correlated frequency band, and irrelevant frequency band file, positive frequency band files and negative frequency band files are established respectively. It should be noted that the classification of shallow, medium and deep acupuncture depths needs to be determined by TCM experts in related fields. Generally, shallow acupuncture depth means the needle tip is about 0.5-1.0 cm, medium acupuncture depth means the needle tip enters the skin about 1.0-2.5 cm, and deep acupuncture depth means the needle tip enters the skin more than 2.5 cm. The acupuncture depths are obtained by the target detection algorithm in the acupuncture data acquisition module. Pre-threshold setting is performed to divide the current acupuncture depth level.

[0024] The frequency bands divided according to the Pearson correlation coefficient are summarized into each positively correlated frequency band, negatively correlated frequency band, and irrelevant frequency band file in combination with the acupuncture depth. The frequency bands are further divided into positive frequency band files and negative frequency band files in combination with the frequency band attributes divided by the real-time efficacy evaluation module. The acupuncture sensitivity and treatment improvement degree under different acupuncture techniques Q and different needle depths are calculated respectively. The specific steps are as follows: For acupuncture sensitivity, the Pearson correlation coefficients of all negative frequency bands extracted from the negative correlation frequency bands under the current acupuncture technique Q were calculated. , calculate the effect size of the negatively correlated frequency band , and its algorithm formula is: ; in, is the number of negative bands in the negative correlation band file, is the negative correlation coefficient of the negative frequency band, It is the product of the absolute value of the negative correlation coefficient and the number of negative frequency bands; Statistically extract the Pearson correlation coefficient of all negative frequency bands from the positive correlation frequency bands under the current acupuncture technique Q , calculate the effect size of the positive correlation band , and its algorithm formula is: ; in, is the number of negative bands in the positive correlation band file, is the positive correlation coefficient of the negative frequency band, is the product of the absolute value of the positive correlation coefficient and the number of negative frequency bands. and Obtaining the patient's acupuncture sensitivity ,in , The larger the value, the greater the acupuncture sensitivity of the current treatment. ; In terms of the improvement of treatment effect, the Pearson correlation coefficients of all positive frequency bands extracted from the negative correlation frequency bands under the current acupuncture technique Q are calculated. , calculate the effect size of the negatively correlated frequency band , and its algorithm formula is: ; in, is the number of positive bands in the negatively correlated band profile, is the negative correlation coefficient of the positive band, It is the product of the absolute value of the negative correlation coefficient and the number of positive frequency bands; Statistically extract the Pearson correlation coefficient of all positive frequency bands in the positive correlation frequency band under the current acupuncture technique Q , calculate the effect size of the positive correlation band , and its algorithm formula is: ; in, is the number of positive bands in the positive correlation band file, is the positive correlation coefficient of the positive frequency band, is the product of the absolute value of the positive correlation coefficient and the number of positive frequency bands. and Obtaining the patient's acupuncture sensitivity ,in , The larger the value, the greater the improvement of the therapeutic effect of the current treatment. The values ​​of ; It should be noted that by adding the positively correlated negative frequency band influence and the negatively correlated negative frequency band influence, a comprehensive value can be obtained. This value represents the degree to which all negative frequency bands have a negative impact on the patient, regardless of whether the frequency band is positively correlated or negatively correlated with the acupuncture depth. In addition, based on the individual differences of different patients, the treatment sensitivity of different patients can be obtained through the negative frequency bands of different patients recorded in the files, thereby evaluating the acupuncture effect of the patients in a targeted manner.

[0025] Calculate the comprehensive impact of different acupuncture depths ,when >0 means the treatment effect is positive. <0 means negative treatment effect. >0, and the acupuncture techniques and acupuncture depths ranked first are selected as the specific treatment plan for the current patient, and the different acupuncture depths under different acupuncture techniques are recorded in the patient portrait file. value.

[0026] The real-time efficacy evaluation module also includes generating a specific efficacy evaluation score for the current patient's treatment based on the patient portrait file established in the patient portrait generation module during the current patient's treatment process, combined with the acupuncture techniques and acupuncture depth during the current patient's treatment process; Through the acupuncture data collection module, the acupuncture technique and acupuncture depth of each acupuncture treatment process are obtained, and the comprehensive impact of different acupuncture techniques and different acupuncture depths of different patients are obtained based on the current patient portrait file. , calculate the patient's treatment-specific efficacy evaluation score, and the algorithm formula is: ; in, represents the patient's specific efficacy evaluation score for this treatment, and i represents the number of acupuncture treatments for the patient.

[0027] It should be noted that the comprehensive impact of each acupuncture treatment on the patient during the current treatment process By adding up the total comprehensive impact of this treatment, we can get the specific efficacy evaluation score of each acupuncture during this treatment, combined with the number of acupuncture treatments. A value greater than 0 means that the treatment is effective, and the larger the value, the better the treatment effect.

[0028] The long-term efficacy comprehensive evaluation module sets long-term efficacy evaluation nodes based on the patient's treatment cycle, and conducts long-term efficacy evaluation on patients in the current cycle in combination with the patient-specific efficacy evaluation scores within the cycle. The specific steps are as follows: Based on the number of treatments n in the current patient's treatment cycle, the long-term efficacy evaluation node is set based on the interval number T, and the patient's treatment cycle is divided into In each stage, the time of each treatment in the current stage is counted separately. After the patient's treatment period is over, the The values ​​are recorded and a line graph is drawn.

[0029] It should be noted that the interval number T is usually set to 5. By analyzing the broken line, when the broken line shows an upward trend, it means that as the treatment progresses, the patient's treatment effect is constantly improving. If the broken line is relatively stable, it means that the treatment effect is in a relatively stable state. When the broken line decreases, it means that there may be problems with the treatment plan, and it is necessary to further find the cause and adjust the treatment plan.

[0030] The present invention discloses a real-time evaluation system for acupuncture treatment effect based on brain-computer interface technology. When in use, the brain-computer data collection module collects the patient's EEG signals before and during treatment based on non-invasive brain-computer interface technology. The acupuncture data collection module collects the doctor's actions during treatment to determine the acupuncture points, acupuncture depth and acupuncture technique during the current patient's treatment. The data is transmitted to the real-time evaluation module for treatment effect. The treatment influencing parameters of the patient under the current condition are obtained in combination with historical diagnosis and treatment data to evaluate the patient's treatment effect in real time. At the same time, through the patient portrait generation module, based on the doctor's acupuncture technique and acupuncture depth during acupuncture treatment, the current patient's treatment feedback EEG signal is associated to generate the patient's treatment portrait file, including the patient's treatment sensitivity and the degree of improvement in treatment effect, to assist doctors in comprehensively determining the best treatment plan, and combine the current treatment acupuncture technique and acupuncture depth to obtain the patient's specific efficacy evaluation score. Through the long-term efficacy comprehensive evaluation module, based on the patient's treatment cycle, a long-term efficacy evaluation node is set, and combined with the patient-specific efficacy evaluation scores within the cycle, the long-term efficacy of patients in the current cycle is further evaluated.

[0031] In the embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation; the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the method of this embodiment.

[0032] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A real-time evaluation system for acupuncture treatment effect based on brain-computer interface technology, characterized in that: It includes brain-computer data collection module, acupuncture data collection module, real-time efficacy evaluation module, patient portrait generation module, and long-term efficacy comprehensive evaluation module; The brain-computer data collection module includes an EEG sensor, which collects the patient's EEG signals before and during treatment based on non-embedded brain-computer interface technology and transmits them to subsequent modules; The acupuncture data acquisition module includes a high-definition camera to collect the doctor's actions during the treatment process, to determine the acupuncture points, acupuncture depth and acupuncture techniques during the current patient treatment process, and to transmit relevant data to subsequent modules; The real-time efficacy evaluation module collects EEG signal data of different patients during treatment under the current condition based on historical diagnosis and treatment data, determines the parameters affecting the treatment effect, and evaluates the treatment effect of the patient in real time based on the changes in EEG signals of the current patient during treatment; The patient portrait generation module generates a treatment portrait of the patient based on the doctor's acupuncture technique and acupuncture depth during acupuncture treatment, and associates the current patient's treatment feedback EEG signal to generate the patient's treatment sensitivity and treatment effect improvement, and comprehensively determine the best treatment plan; The long-term efficacy comprehensive evaluation module sets long-term efficacy evaluation nodes based on the patient's treatment cycle, and conducts long-term efficacy evaluation on patients in the current cycle in combination with the patient-specific efficacy evaluation scores within the cycle.

2. According to claim 1, a real-time evaluation system for acupuncture treatment effect based on brain-computer interface technology is characterized in that: The acupuncture data acquisition module includes a high-definition camera to collect the doctor's actions during the treatment process, to determine the acupuncture points, acupuncture depth and acupuncture techniques during the current patient treatment process, and to transmit relevant data to subsequent modules, including the following steps: The doctor's acupuncture movements are captured by a high-definition camera, and the video stream of the treatment process is collected. The body parts in the video stream are identified by the target detection algorithm, and the characteristic parameters of the acupuncture parts are recorded. The acupuncture points of the current patient are determined by cosine similarity comparison. Extract the initial length of the needle in the video stream through the target detection algorithm , combined with the remaining length of the needle after acupuncture , calculate the acupuncture depth ; Regarding acupuncture techniques, high-definition video data of different doctors performing various acupuncture techniques are collected, and key features of acupuncture hand movements are extracted, including movement type, movement direction, and movement amplitude. Training sets and test sets are established for different acupuncture techniques, and the acupuncture technique model is trained through convolutional neural networks. The acupuncture feature data in the current video stream is substituted frame by frame into the trained neural network acupuncture technique model, and the degree of matching between the current frame and each known technique model is calculated. The acupuncture technique is determined based on the similarity value.

3. The real-time evaluation system for acupuncture treatment effect based on brain-computer interface technology according to claim 1 is characterized in that: The real-time efficacy evaluation module collects EEG signal data of different patients during treatment under the current condition based on historical diagnosis and treatment data, determines the parameters affecting the treatment effect, and evaluates the treatment effect of the patient in real time in combination with the changes in brain-computer signals during the current patient's treatment. The specific steps are as follows: Collect historical patient diagnosis and treatment data of the same disease, combine the EEG signal data of different patients during the treatment of the current disease, divide the EEG signal bands, and distinguish between positive and negative EEG signal bands, determine the parameters affecting the treatment effect, and combine the EEG signal changes of the current patient during the treatment process to evaluate the patient's treatment effect in real time. The specific steps are as follows: According to the frequency range of EEG signal fluctuations of patients collected during historical treatment, the EEG signals are divided into different frequency bands. The collected EEG signals are converted from the time domain to the frequency domain through fast Fourier transform, the power spectrum density of each frequency component is calculated, and the signal characteristics of different frequency bands are determined; Based on the historical disease diagnosis and treatment data set and the current patient treatment feedback and symptom changes, the association between different frequency bands and treatment effects is determined, that is, the fluctuation frequency bands when the patient's symptoms are relieved and the fluctuation frequency bands when the patient's pain is aggravated or the symptoms are worsened are recorded, and the former are divided into positive EEG signal bands, and the latter are divided into negative EEG signal bands; According to the initial power spectral density of each frequency band of the patient before treatment, combined with the power spectral density of each frequency band after the treatment is completed, the fluctuation values ​​of different frequency bands in the positive frequency band and the fluctuation values ​​of different frequency bands in the negative frequency band are obtained. By multiplying the fluctuation value of the frequency band with the weight coefficient corresponding to the frequency band, accumulating the products of each frequency band in the positive frequency band, accumulating each product in the negative frequency band, and finally summing the accumulated values ​​of the positive frequency band and the accumulated values ​​of the negative frequency band, the real-time efficacy evaluation score during the treatment is obtained. When the real-time efficacy evaluation score is greater than 0, it means that the treatment has a positive effect. When the real-time efficacy evaluation score is less than 0, it means that the treatment has a negative effect.

4. The real-time evaluation system for acupuncture treatment effect based on brain-computer interface technology according to claim 2 is characterized in that: The patient portrait generation module generates a treatment portrait of the patient based on the doctor's acupuncture technique and acupuncture depth during acupuncture treatment, and associates the current patient's treatment feedback EEG signal to generate the patient's treatment sensitivity and treatment effect improvement, and comprehensively determine the best treatment plan. The specific steps are: Establish a timestamp based on the changes in the EEG signals during the patient's treatment process, and simultaneously establish a timestamp for the acupuncture data during the patient's treatment process, and associate the acupuncture data and brain-computer data during the current patient's treatment process; Based on the division results of feedback EEG signals in the real-time efficacy evaluation module, positive feedback EEG signal data and negative feedback EEG signal data are obtained. Combined with the correlation between relevant feedback EEG signal data and acupuncture data, the patient's treatment portrait is generated, including the treatment sensitivity of different acupuncture data to the patient and the degree of improvement in treatment effect, and the best treatment plan is comprehensively determined.

5. The real-time evaluation system for acupuncture treatment effect based on brain-computer interface technology according to claim 4 is characterized in that: The method establishes a timestamp based on the changes in the EEG signal during the patient's treatment process, and simultaneously establishes a timestamp for the acupuncture data during the patient's treatment process, and associates the acupuncture data and brain-computer data during the current patient's treatment process, and the specific steps are: Based on different acupuncture techniques, the corresponding timestamps of acupuncture depth and different EEG signal frequency band fluctuations under the corresponding acupuncture techniques are established, and the EEG signal frequency bands that are positively or negatively correlated with the acupuncture depth under the corresponding acupuncture techniques are calculated. The specific steps are: In the EEG signal data, the acupuncture technique and acupuncture depth corresponding to each time point are marked, and the power spectrum density of the specific frequency band of the EEG signal fluctuation is matched according to the timestamp. The correlation between the acupuncture depth under the current acupuncture technique and the corresponding EEG signal characteristic fluctuation is calculated by the Pearson correlation coefficient: The Pearson correlation coefficient between the acupuncture depth and the power spectral density fluctuation of different EEG signal specific frequency bands under the current acupuncture technique is calculated respectively. The specific algorithm formula is: ； in, Represents the depth of acupuncture under acupuncture technique Q, represents the power spectrum density value of EEG signal fluctuation in frequency band a, Represents the Pearson correlation coefficient of the acupuncture depth under acupuncture manipulation Q and the power spectrum density value of the EEG signal fluctuation under frequency band a; in, The value range is from -1 to 1. When <0, it means that the depth of needle y under acupuncture technique Q is negatively correlated with the frequency band a, that is, when one variable increases, the other variable decreases; when When ≈0, it means that the needle depth y under acupuncture technique Q is unrelated to the frequency band a, that is, when one variable increases or decreases, the other variable does not change; when When >0, it means that the needle depth y under acupuncture technique Q is positively correlated with the frequency band a, that is, when one variable increases, the other variable increases.

6. The real-time evaluation system for acupuncture treatment effect based on brain-computer interface technology according to claim 5 is characterized in that: The real-time efficacy evaluation module is based on the division result of the feedback EEG signals to obtain positive feedback EEG signal data and negative feedback EEG signal data, and the correlation between the relevant feedback EEG signal data and acupuncture data is combined to generate a treatment portrait of the patient, including the treatment sensitivity of different acupuncture data to the patient and the degree of improvement of the treatment effect, and comprehensively determine the best treatment plan. The specific steps are: The frequency band a that is correlated with the needling depth y under the same acupuncture technique Q is counted, and a patient acupuncture database is established through MySQL. A patient portrait file is established in the database and the file is subdivided based on the type of acupuncture technique Q. In each acupuncture technique Q file, files for shallow, medium, and deep needling depths are established respectively. In the files for shallow, medium, and deep needling depths, positively correlated frequency bands, negatively correlated frequency bands, and irrelevant frequency bands are established. In each positively correlated frequency band, negatively correlated frequency band, and irrelevant frequency band file, positive frequency band files and negative frequency band files are established respectively. The frequency bands divided according to the Pearson correlation coefficient are summarized into each positively correlated frequency band, negatively correlated frequency band, and irrelevant frequency band file in combination with the acupuncture depth. The frequency bands are further divided into positive frequency band files and negative frequency band files in combination with the frequency band attributes divided by the real-time efficacy evaluation module. The acupuncture sensitivity and treatment improvement degree under different acupuncture techniques Q and different needle depths are calculated respectively. The specific steps are as follows: For acupuncture sensitivity, the Pearson correlation coefficients of all negative frequency bands extracted from the negative correlation frequency bands under the current acupuncture technique Q were calculated. , calculate the effect size of the negatively correlated frequency band , and its algorithm formula is: ； in, is the number of negative bands in the negative correlation band file, is the negative correlation coefficient of the negative frequency band, It is the product of the absolute value of the negative correlation coefficient and the number of negative frequency bands; Statistically extract the Pearson correlation coefficient of all negative frequency bands from the positive correlation frequency bands under the current acupuncture technique Q , calculate the effect size of the positive correlation band , and its algorithm formula is: ； in, is the number of negative bands in the positive correlation band file, is the positive correlation coefficient of the negative frequency band, is the product of the absolute value of the positive correlation coefficient and the number of negative frequency bands. and Obtaining the patient's acupuncture sensitivity ,in , The larger the value, the greater the acupuncture sensitivity of the current treatment. ; In terms of the improvement of treatment effect, the Pearson correlation coefficients of all positive frequency bands extracted from the negative correlation frequency bands under the current acupuncture technique Q are calculated. , calculate the effect size of the negatively correlated frequency band , and its algorithm formula is: ； in, is the number of positive bands in the negatively correlated band profile, is the negative correlation coefficient of the positive band, It is the product of the absolute value of the negative correlation coefficient and the number of positive frequency bands; Statistically extract the Pearson correlation coefficient of all positive frequency bands in the positive correlation frequency band under the current acupuncture technique Q , calculate the effect size of the positive correlation band , and its algorithm formula is: ； in, is the number of positive bands in the positive correlation band file, is the positive correlation coefficient of the positive frequency band, is the product of the absolute value of the positive correlation coefficient and the number of positive frequency bands. and Obtaining the patient's acupuncture sensitivity ,in , The larger the value, the greater the improvement of the therapeutic effect of the current treatment. The values ​​of ; Calculate the comprehensive impact of different acupuncture depths ,when >0 means the treatment effect is positive. <0 means negative treatment effect. >0, and the acupuncture techniques and acupuncture depths ranked first are selected as the specific treatment plan for the current patient, and the different acupuncture depths under different acupuncture techniques are recorded in the patient portrait file. value.

7. The real-time evaluation system for acupuncture treatment effect based on brain-computer interface technology according to claim 6 is characterized in that: The real-time efficacy evaluation module also includes generating a specific efficacy evaluation score for the current patient's treatment based on the patient portrait file established in the patient portrait generation module during the current patient's treatment, combined with the acupuncture technique and acupuncture depth during the current patient's treatment; Through the acupuncture data collection module, the acupuncture technique and acupuncture depth of each acupuncture treatment process are obtained, and the comprehensive impact of different acupuncture techniques and different acupuncture depths of different patients are obtained based on the current patient portrait file. , calculate the patient's treatment-specific efficacy evaluation score, and the algorithm formula is: ； in, represents the patient's specific efficacy evaluation score for this treatment, and i represents the number of acupuncture treatments for the patient.

8. The real-time evaluation system for acupuncture treatment effect based on brain-computer interface technology according to claim 7 is characterized in that: The long-term efficacy comprehensive evaluation module sets a long-term efficacy evaluation node based on the patient's treatment cycle, and performs a long-term efficacy evaluation on the patients in the current cycle in combination with the patient-specific efficacy evaluation score in the cycle. The specific steps are as follows: Based on the number of treatments n in the current patient's treatment cycle, the long-term efficacy evaluation node is set based on the interval number T, and the patient's treatment cycle is divided into In each stage, the time of each treatment in the current stage is counted separately. After the patient's treatment period is over, the The values ​​are recorded and a line graph is drawn.

9. The real-time evaluation system for acupuncture treatment effect based on brain-computer interface technology according to claim 1 is characterized in that: The brain-computer data collection module includes an EEG sensor, which collects the patient's EEG signals before and during treatment based on non-invasive brain-computer interface technology and transmits them to subsequent modules. The specific steps are as follows: Select appropriate EEG sensors, including non-invasive dry electrodes and wet electrodes, to be placed on the patient's forehead and scalp area. Use non-invasive brain-computer interface technology to capture the patient's EEG signal frequency bands before and during treatment, and add a timestamp to each EEG signal sample.

Images