MST electrical stimulation amount determination method and device

Abstract

The invention discloses an MST electrical stimulation amount determination method. The method comprises the following steps: acquiring basic identity data, physiological parameter data, medical file data and electrical stimulation application indications of a target stimulation user; inputting the basic identity data, the physiological parameter data, the medical file data and the electrical stimulation application indications into an electrical stimulation quantity generation model to obtain a target stimulation quantity output by the electrical stimulation quantity generation model; the electrical stimulation quantity generation model is obtained by training sample influence data and corresponding stimulation quantity label results; and transmitting electrical stimulation to the target stimulation user based on the target stimulation amount. The method can achieve the personalized and precise determination of the electrical stimulation amount of a patient through the electrical stimulation amount generation model, fits the individual difference to the greatest extent, improves the pertinence and effectiveness of electrical stimulation treatment, reduces the early-stage preparation time of medical workers, gets rid of the limitation of the traditional judgment purely depending on experience, and improves the accuracy of electrical stimulation treatment. And the determination of the electrical stimulation amount is more scientific, reasonable and intelligent.

Description

Technical Field

[0001] The present invention relates to the field of neuroscience technologies, and particularly to a method and device for determining the MST electrical stimulation amount. Background Art

[0002] The MST (Magnetic seizure therapy) technology is a biological stimulation technology that emerged in the mid-1980s to affect and change brain functions. And with the development of the technology, its application in clinical medicine has increasingly attracted people's attention. MST is a biological stimulation technology that uses a time-varying magnetic field to act on the motor cortex of the brain to generate an induced current to change the action potential of cortical nerve cells, thereby affecting brain metabolism and neural electrical activities. And for some stimulations that change brain functions, it is required that the motor cortex of the brain produces convulsions. In medical rehabilitation, for patients with muscle atrophy caused by nerve damage, MST electrical stimulation can help maintain the function and morphology of muscles and prevent the further development of muscle atrophy. The principle is that in muscle electrical stimulation, MST transmits electrical pulses with specific frequencies and intensities to muscle tissues through electrodes. These electrical pulses can simulate nerve impulses and cause muscle contractions.

[0003] With the development of the MST technology and the changes in technical equipment, the MST technology has begun to be gradually applied. In the MST technology, if the electrical stimulation amount is too low, it will have no effect on muscle or body nerve cells. If the electrical stimulation amount is too high, it will cause physical discomfort, resulting in excessive pain and damage to the body. Therefore, in the use of the MST technology, the determination of the electrical stimulation amount is crucial. However, currently, the electrical stimulation amount for patients generally relies on doctors to make a preliminary judgment based on the patient's physical condition, and then manually adjust the gradual increase of the electrical stimulation amount until the ideal electrical stimulation amount state is reached. In this process, the manual adjustment method highly depends on the operator's experience and judgment, and there may be significant differences in the measurement results between different operators. Therefore, in the absence of accurate judgment of the electrical stimulation amount, it takes doctors a lot of time and energy to judge the electrical stimulation amount of patients during each diagnosis process, and the results are unstable while also affecting the overall work efficiency. Summary of the Invention

[0004] The purpose of the present invention is to solve the problems in the prior art, and to propose a method and device for determining the MST electrical stimulation amount.

[0005] To achieve the above purpose, the present invention adopts the following technical solutions:

[0006] The method for determining the MST electrical stimulation amount includes the following steps:

[0007] Obtain the basic identity data, physiological parameter data, medical record data, and electrical stimulation application indications of the target stimulated user;

[0008] Input the basic identity data, the physiological parameter data, the medical record data, and the electrostimulation application indication into an electrostimulation dose generation model to obtain a target stimulation dose output by the electrostimulation dose generation model; the electrostimulation dose generation model is trained by sample influence data and its corresponding stimulation dose label results;

[0009] Based on the target stimulation dose, emit an electrostimulation to the target stimulation user.

[0010] According to the MST electrostimulation dose determination method provided by the present invention, the electrostimulation application indication includes the electrostimulation purpose and the electrostimulation area; the electrostimulation purpose is at least any one of pain relief, muscle rehabilitation training, and nerve function recovery.

[0011] According to the MST electrostimulation dose determination method provided by the present invention, the basic identity data includes the age and gender of the target stimulation user; the physiological parameter data includes the muscle parameters and nerve sensitivity parameters of the target stimulation user.

[0012] According to the MST electrostimulation dose determination method provided by the present invention, the nerve sensitivity parameters include the current perception threshold, the vibration perception threshold, and the nerve conduction velocity; the medical record data includes the past medical history, surgical history, current medication situation, and family genetic history of the target stimulation user.

[0013] According to the MST electrostimulation dose determination method provided by the present invention, the training steps of the electrostimulation dose generation model include:

[0014] Obtain sample influence data, input the sample influence data into a pre-trained model to obtain a target prediction result output by the pre-trained model; obtain a loss value based on the loss function of the pre-trained model according to the target prediction result; adjust the optimization objective function in the pre-trained model based on the loss value; predict the prediction result of the sample influence data based on the adjusted pre-trained model until the loss value output by the loss function is less than or equal to a first preset threshold, the difference between adjacent two groups of loss values is greater than zero, and the difference between adjacent two groups of loss values is less than a second preset threshold.

[0015] According to the MST electrostimulation dose determination method provided by the present invention, the target stimulation dose output by the electrostimulation dose generation model includes current intensity, stimulation frequency, pulse width, and stimulation time, and the loss function is:

[0016]

[0017] ; where, represents the electrostimulation dose predicted by the model for the i-th sample; y iRepresents the actual amount of electrical stimulation for the i-th sample; n represents the total number of samples; θ j Represents the over-stimulation threshold for the j-th parameter of the electrical stimulation amount; k j Represents the penalty coefficient for the j-th parameter of the electrical stimulation amount; m represents the number of parameters of the electrical stimulation amount; Represents the value of the j-th parameter in the electrical stimulation amount predicted by the model for the i-th sample; x ij Represents the j-th feature in the input data vector of the i-th sample, u j Represents the mean of the j-th feature among all samples, σ j Represents the standard deviation of the j-th feature among all samples, r i Represents the risk coefficient for the j-th feature; p represents the number of features of the input sample data; α, β represent trade-off coefficients.

[0018] According to the MST electrical stimulation amount determination method provided by the present invention, the optimization objective function is:

[0019] J = L zo +γ*‖ω‖ 2

[0020] ; where ω represents the weight vector of the model, and γ represents the regularization coefficient.

[0021] The MST electrical stimulation amount determination device includes:

[0022] An acquisition unit: used to acquire the basic identity data, physiological parameter data, medical record data, and electrical stimulation application indications of the target stimulated user;

[0023] A calculation unit: used to input the basic identity data, the physiological parameter data, the medical record data, and the electrical stimulation application indications into the electrical stimulation amount generation model to obtain the target stimulation amount output by the electrical stimulation amount generation model; the electrical stimulation amount generation model is trained by sample influence data and its corresponding stimulation amount label results;

[0024] An output unit: used to emit electrical stimulation to the target stimulated user based on the target stimulation amount.

[0025] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps of the MST electrical stimulation amount determination method according to any one of claims 1 to 7 are implemented.

[0026] The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the MST electrical stimulation amount determination method according to any one of claims 1 to 7 are implemented.

[0027] The present invention has the following advantages compared with the prior art:

[0028] The MST electric stimulation dose determination method and device provided by the present invention obtain various factors such as the basic identity data, physiological parameter data, medical record data, and electric stimulation application indications of the user, and realize the personalized and accurate determination of the electric stimulation dose for the patient through the electric stimulation dose generation model, which maximally conforms to individual differences, improves the pertinence and effectiveness of electric stimulation treatment, reduces the pre-preparation time of medical staff, and gets rid of the limitations of traditional experience-based judgment, making the determination of the electric stimulation dose more scientific, reasonable and intelligent. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0030] Figure 1 It is a schematic flowchart of the MST electric stimulation dose determination method provided by an embodiment of the present invention;

[0031] Figure 2 It is a schematic structural diagram of the MST electric stimulation dose determination device provided by an embodiment of the present invention;

[0032] Figure 3 It is a schematic structural diagram of the electronic device proposed by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0033] To make the objectives, technical solutions and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention in conjunction with the drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments in the present invention belong to the scope of protection of the present invention.

[0034] The following will be combined with Figure 1 - Figure 3 Describe the MST electric stimulation dose determination method and device of the present invention.

[0035] Figure 1 It is a schematic flowchart of the MST electric stimulation dose determination method provided by the present invention. As Figure 1 shown, the method includes:

[0036] Step 101, obtain the basic identity data, physiological parameter data, medical record data, and electric stimulation application indications of the target stimulation user.

[0037] Specifically, the basic identity data includes the age and gender of the target stimulation user; the physiological parameter data includes the muscle parameters and nerve sensitivity parameters of the target stimulation user. Since age is one of the key factors affecting the amount of electrical stimulation, the physiological functions of the human body are different at different ages, and there are differences in the tolerance and response characteristics to electrical stimulation. In terms of gender, generally, the skin of women is relatively thinner and the nerve distribution is more dense, so they may be more sensitive to electrical stimulation under the same conditions, which also affects the determination of the appropriate amount of electrical stimulation. Therefore, when determining the amount of electrical stimulation for the target stimulation user, the gender and age of the target stimulation user are first determined.

[0038] At the same time, the physiological parameter data includes the muscle parameters and nerve sensitivity parameters of the target stimulation user. Among them, the muscle parameters are accurately measured by professional testing methods. For example, the maximum contractile force and muscle endurance time of the main muscle groups are accurately measured by using an isokinetic muscle strength tester, and the body-wide and local muscle mass and the ratio of muscle to fat are estimated by using bioelectrical impedance analysis technology. This is because individuals with strong muscle strength and rich muscle mass require a relatively higher amount of electrical stimulation to achieve further muscle function improvement or rehabilitation stimulation. In terms of nerve sensitivity parameters, nerve conduction velocity (NCV) tests can be performed, including the detection of motor nerve conduction velocity (MCV) and sensory nerve conduction velocity (SCV), and at the same time, nerve excitability threshold tests are carried out, such as current perception threshold determination. Among them, the nerve conduction velocity can reflect the conduction efficiency of nerve impulses in nerve fibers, and the current perception threshold reflects the sensitivity of the nerve to current stimulation. In practice, if the nerve conduction velocity of the target stimulation user is slow or the nerve excitability threshold is low, then when setting the amount of electrical stimulation, corresponding parameters need to be adjusted, such as reducing the current intensity and optimizing the stimulation frequency, to ensure that the electrical stimulation can achieve the expected effect without causing excessive stimulation or damage to the nerves. After measuring the muscle parameters and nerve sensitivity parameters in the above manner, they are pre-stored in the medical record database, and the corresponding muscle parameters and nerve sensitivity parameters are obtained through the name of the target stimulation user.

[0039] On the other hand, the indications for electrical stimulation application include the purpose of electrical stimulation and the area of electrical stimulation; the purpose of electrical stimulation is at least one of pain relief, muscle rehabilitation training, and nerve function recovery. During the process of determining the amount of electrical stimulation, different purposes of electrical stimulation correspond to quite different requirements for the amount of electrical stimulation. If the purpose is pain relief, generally only a relatively low amount of electrical stimulation is needed to stimulate the relevant nerve fibers and activate the endogenous analgesic system. Usually, the amount of electrical stimulation that can make the patient feel a slight tingling sensation is appropriate. If muscle rehabilitation training is carried out, such as for muscle atrophy caused by long-term bed rest or injury, a relatively higher amount of electrical stimulation that can cause obvious muscle contraction is required to gradually enhance muscle strength and endurance. Therefore, when determining the amount of electrical stimulation for the target stimulation user, first determine the purpose of electrical stimulation, and then determine the area of electrical stimulation. This is because different body parts have different sensitivities and response characteristics to electrical stimulation. Parts with dense nerve distribution and close to important organs, such as the face and neck, are more sensitive to electrical stimulation and require a relatively smaller amount of electrical stimulation; while parts with thick muscles, such as the buttocks and thighs, often require a higher amount of electrical stimulation to effectively stimulate the deep muscles for purposes such as muscle strength training. The purpose of electrical stimulation and the area of electrical stimulation are input into the MST electrical stimulation amount determination device and saved when the target stimulation user fills out the form.

[0040] Furthermore, the medical record data includes the target stimulation user's past medical history, surgical history, current medication situation, and family genetic history. When determining the amount of electrical stimulation, it is also necessary to deeply sort out the target stimulation user's past medical history and focus on those disease conditions that may affect the effect and safety of electrical stimulation. For example, patients with cardiovascular diseases have a lower tolerance of the heart to electrical stimulation because electrical stimulation may interfere with the normal electrophysiological activities of the heart and cause serious consequences such as arrhythmia. Therefore, when determining the amount of electrical stimulation, great caution must be exercised and parameters such as the current intensity must be strictly controlled. In addition, the surgical history is also an important consideration factor, especially the surgical sites involving nerves, muscles, or bones. Finally, it is also necessary to comprehensively understand the medication situation of the user. Some medications have the effect of changing the excitability or conductivity of nerves and muscles. Therefore, when determining the amount of electrical stimulation, obtaining the medical record data of the target stimulation user through the medical record data system is one of the factors for judging the amount of electrical stimulation.

[0041] Step 102: Input the basic identity data, physiological parameter data, medical record data, and electrical stimulation application indications into the electrical stimulation amount generation model to obtain the target stimulation amount output by the electrical stimulation amount generation model; the electrical stimulation amount generation model is trained by sample influence data and its corresponding stimulation amount label results.

[0042] Specifically, the sample mapping data includes the basic identities, physiological parameters, medical records of different individuals, as well as the purpose of electrical stimulation and the electrical stimulation area. Before the above data is input into the electrical stimulation amount generation model, it is first processed as much as possible to be standardized to form a comparable and general data format. In one embodiment, for age data, normalization processing can be performed to map the age to a specific interval range (such as 0 - 1), and the normalization formula is: where A 标准化 represents the normalized age value, Age represents the actual age, Age min represents the minimum value of the set age range, Age max represents the maximum value of the set age range. For gender data, binary coding is used, with males coded as 0 and females coded as 1. For muscle parameters in physiological parameter data, they are standardized according to the average value and standard deviation of healthy people of the same age and gender. The formula is: where M 标准化 represents the normalized muscle parameter value, M us represents the actually measured muscle parameter value, μMS represents the average value of muscle parameters in the same population, and σMS represents the standard deviation of muscle parameters in the same population. For nerve sensitivity parameters in physiological parameter data, the same method as for muscle parameter standardization is used. For disease history in medical record data, it can be classified and coded according to the International Classification of Diseases (ICD) and converted into digital form for model processing. For the purpose of electrical stimulation and the electrical stimulation area, classification coding is used. Relieving pain is coded as P01, muscle rehabilitation training is coded as P02, nerve function recovery is coded as P03, the head area in the electrical stimulation area is coded as H01, the neck area is coded as H02, the upper limb area is coded as H03, the lower limb area is coded as H04, and the trunk part is coded as H05. Thus, all the data input into the electrical stimulation amount generation model is unified into a format that can be received by the model.

[0043] Furthermore, input the basic identity data, physiological parameter data, medical record data, and electrostimulation application indications of the target-stimulated user into the electrostimulation dose generation model according to the established data format and order. Based on the rules and algorithms it has learned internally, the model comprehensively analyzes and processes this input information, and finally outputs the target electrostimulation dose for this user, that is, specific parameter values such as current intensity, stimulation frequency, pulse width, and stimulation time. For example, for a 45-year-old male patient with lumbar muscle strain, after inputting his basic identity data (age, gender, etc.), physiological parameter data (lumbar muscle strength test value, related nerve conduction velocity, etc.), medical record data (no other major disease history, not taking special drugs that affect neuromuscular function, etc.), and electrostimulation application indications (relieving lumbar pain, stimulating area is the lumbar muscle group) into the model, after calculation, the model may output an appropriate current intensity of 10 mA, a stimulation frequency of 20 Hz, a pulse width of 200 μs, and a stimulation time of 20 minutes each time as the electrostimulation dose parameters.

[0044] Applying electrostimulation with the target electrostimulation dose output by the above model can fully consider the various individual differences and specific application requirements, achieve personalized customization of the electrostimulation dose, improve the pertinence and effectiveness of electrostimulation treatment, reduce the occurrence probability of problems such as poor treatment effect and patient discomfort caused by inappropriate electrostimulation dose, and enhance the overall quality and safety of electrostimulation treatment.

[0045] Step 103: Based on the target electrostimulation dose, emit electrostimulation to the target-stimulated user.

[0046] Specifically, according to the target electrostimulation dose output by the model, select a professional and suitable electrostimulation device (such as a neuromuscular electrical stimulator, transcutaneous electrical nerve stimulator, etc.), and after accurately setting parameters such as the output current intensity, stimulation frequency, pulse width, and stimulation time, after the operator is familiar with the operation, prepare the device for electrostimulation emission.

[0047] Furthermore, during the process of emitting electrostimulation to the target-stimulated user, it is also necessary to closely monitor the user's reaction. On the one hand, pay attention to the user's subjective feelings, such as whether there are abnormal sensations such as pain, discomfort, excessive tingling, etc., and communicate with the user in a timely manner to understand their experience; on the other hand, through professional monitoring means, observe some objective physiological indicators in real time, such as the changes in heart rate and blood pressure, and the contraction state of the muscles in the stimulation area. If it is found that the user has obvious discomfort reactions or abnormal fluctuations in objective indicators, it indicates that the current electrostimulation dose may not be appropriate, and it is necessary to adjust the electrostimulation dose in a timely manner. If necessary, stop the electrostimulation operation, re-evaluate the user's relevant data, and determine a more appropriate electrostimulation dose through the electrostimulation dose generation model again and then continue to implement.

[0048] The present invention relates to the field of neuroscience, and provides a method and device for determining the MST electrical stimulation dosage. In the present invention, the method for determining the MST electrical stimulation dosage first obtains various factors such as the user's basic identity data, physiological parameter data, medical record data, and electrical stimulation application indications, and uses an electrical stimulation dosage generation model to achieve personalized and precise determination of the patient's electrical stimulation dosage, maximizing the adaptation to individual differences, improving the pertinence and effectiveness of electrical stimulation treatment, reducing the pre-preparation time of medical staff, and getting rid of the limitations of traditional reliance on experience judgment alone, making the determination of electrical stimulation dosage more scientific, reasonable, and intelligent.

[0049] Correspondingly, in step 102, the training steps of the electrical stimulation dosage generation model include:

[0050] Obtain sample influence data, input the sample influence data into a pre-trained model to obtain a target prediction result output by the pre-trained model; obtain a loss value based on the loss function of the pre-trained model according to the target prediction result; adjust the optimization objective function in the pre-trained model based on the loss value; predict the prediction result of the sample influence data based on the adjusted pre-trained model until the loss value output by the loss function is less than or equal to a first preset threshold, the difference between two adjacent groups of loss values is greater than zero, and the difference between two adjacent groups of loss values is less than a second preset threshold.

[0051] Specifically, when collecting sample influence data, a large amount of sample data related to the determination of electrical stimulation dosage can be collected from multiple medical institutions, rehabilitation centers, and relevant scientific research institutions, covering populations of different ages, genders, and races to ensure the diversity and representativeness of the samples. For example, in terms of age range, it includes children, adolescents, adults, and the elderly; in terms of gender, data of both males and females are collected evenly; in terms of health status, data of both healthy individuals and patients with various diseases (such as cardiovascular diseases, diabetes, neurological diseases, etc.) are included. At the same time, the collected data also involves different electrical stimulation application scenarios, such as pain treatment, muscle rehabilitation training, nerve function repair, etc., and different electrical stimulation regions, including relevant data of various body parts such as the upper limbs, lower limbs, trunk, and head. As much as possible, the sample influence data is made more comprehensive and rich.

[0052] In addition, after the original data, the original data is first sorted and cleaned to remove invalid, duplicate, or incorrect data records. Then, feature extraction is performed to convert the original data into sample impact data that the model can process. And the pre-trained model is based on a recurrent neural network or a convolutional neural network. The sorted sample impact data is input into the pre-trained model. The model performs a series of calculations and processes on the input data according to its existing parameter settings and internal structure. In a neural network, the data first enters the model through the input layer, then further feature extraction and transformation are performed in the hidden layer, and a non-linear transformation is performed through the activation function of the neurons (such as ReLU, Sigmoid, etc.), and finally the predicted electrostimulation amount result is output in the output layer. This prediction result is a vector containing electrostimulation parameters such as current intensity, stimulation frequency, pulse width, and stimulation time.

[0053] The target stimulation amount output by the electrostimulation amount generation model includes current intensity, stimulation frequency, pulse width, and stimulation time, and the loss function is:

[0054]

[0055]

[0056] Among them, represents the electrostimulation amount predicted by the model for the i-th sample; y i represents the actual electrostimulation amount of the i-th sample; n represents the total number of samples; θ j represents the over-stimulation threshold of the j-th parameter of the electrostimulation amount; k j represents the penalty coefficient for the j-th electrostimulation amount parameter; m represents the number of electrostimulation amount parameters; represents the value of the j-th parameter in the electrostimulation amount predicted by the model for the i-th sample; x ij represents the j-th feature in the input data vector of the i-th sample, u j represents the mean value of the j-th feature in all samples, σ j represents the standard deviation of the j-th feature in all samples, r i represents the risk coefficient for the j-th feature; p represents the number of input sample data features; α and β represent trade-off coefficients.

[0057] The optimization objective function is:

[0058] J = L zo + γ * ‖ω‖ 2

[0059] ; where ω represents the weight vector of the model, and γ represents the regularization coefficient.

[0060] Figure 2It is a schematic structural diagram of a preview speed planning device based on a continuous trajectory provided by the present invention. As Figure 2 shown, the device includes: an acquisition unit 10: configured to acquire basic identity data, physiological parameter data, medical record data, and electrostimulation application indications of a target stimulated user; a calculation unit 20: configured to input the basic identity data, the physiological parameter data, the medical record data, and the electrostimulation application indications into an electrostimulation amount generation model to obtain a target electrostimulation amount output by the electrostimulation amount generation model; the electrostimulation amount generation model is trained by sample influence data and its corresponding stimulation amount label results; an output unit 30: configured to emit electrostimulation to the target stimulated user based on the target electrostimulation amount.

[0061] Figure 3 It is a schematic structural diagram of an electronic device provided by the present invention. As Figure 3 shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330, and a communication bus 340. Among them, the processor 33, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 33 can call logic instructions in the memory 330 to execute the MST electrostimulation amount determination method, which includes: acquiring basic identity data, physiological parameter data, medical record data, and electrostimulation application indications of a target stimulated user; inputting the basic identity data, the physiological parameter data, the medical record data, and the electrostimulation application indications into an electrostimulation amount generation model to obtain a target electrostimulation amount output by the electrostimulation amount generation model; the electrostimulation amount generation model is trained by sample influence data and its corresponding stimulation amount label results; emitting electrostimulation to the target stimulated user based on the target electrostimulation amount.

[0062] In addition, when the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present invention. And the aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical disks, etc., which can store program codes.

[0063] On the other hand, the present invention also provides a computer program product. The computer program product includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the MST electrical stimulation amount determination method provided by each of the above methods. The method includes: obtaining basic identity data, physiological parameter data, medical record data, and electrical stimulation application indications of a target stimulation user; inputting the basic identity data, the physiological parameter data, the medical record data, and the electrical stimulation application indications into an electrical stimulation amount generation model to obtain a target stimulation amount output by the electrical stimulation amount generation model; the electrical stimulation amount generation model is trained by sample influence data and its corresponding stimulation amount label results; and based on the target stimulation amount, emitting electrical stimulation to the target stimulation user.

[0064] In another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is configured to execute the MST electrical stimulation amount determination method provided by each of the above. The method includes: obtaining basic identity data, physiological parameter data, medical record data, and electrical stimulation application indications of a target stimulation user; inputting the basic identity data, the physiological parameter data, the medical record data, and the electrical stimulation application indications into an electrical stimulation amount generation model to obtain a target stimulation amount output by the electrical stimulation amount generation model; the electrical stimulation amount generation model is trained by sample influence data and its corresponding stimulation amount label results; and based on the target stimulation amount, emitting electrical stimulation to the target stimulation user.

[0065] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0066] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, also by hardware. Based on this understanding, the above technical solution, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0067] As described above, it is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, making equivalent substitutions or changes, shall be covered by the protection scope of the present invention.

Claims

1. Method for determining MST electrical stimulation amount, characterized in that It includes the following steps: Obtain the basic identity data, physiological parameter data, medical record data, and electrical stimulation application indications of the target stimulated user; Input the basic identity data, the physiological parameter data, the medical record data, and the electrical stimulation application indications into an electrical stimulation amount generation model to obtain the target stimulation amount output by the electrical stimulation amount generation model; the electrical stimulation amount generation model is trained by sample influence data and its corresponding stimulation amount label results; Based on the target stimulation amount, emit electrical stimulation to the target stimulated user.

2. The MST electrical stimulation amount determination method according to claim 1, wherein The electrical stimulation application indications include the purpose of electrical stimulation and the electrical stimulation area; the purpose of electrical stimulation is at least one of relieving pain, muscle rehabilitation training, and nerve function recovery.

3. The method for determining the MST electrical stimulation amount according to claim 1, wherein The basic identity data includes the age and gender of the target stimulated user; The physiological parameter data includes the muscle parameters and nerve sensitivity parameters of the target stimulated user.

4. The MST electrical stimulation amount determination method according to claim 3, wherein The nerve sensitivity parameters include the current perception threshold, vibration perception threshold, and nerve conduction velocity; the medical record data includes the past medical history, surgical history, current medication situation, and family genetic history of the target stimulated user.

5. The MST electrical stimulation amount determination method according to claim 1, characterized in that, The training steps of the electrical stimulation amount generation model include: Obtain sample influence data, input the sample influence data into a pre-trained model to obtain the target prediction result output by the pre-trained model; obtain a loss value based on the loss function of the pre-trained model according to the target prediction result; adjust the optimization objective function in the pre-trained model based on the loss value; predict the prediction result of the sample influence data based on the adjusted pre-trained model until the loss value output by the loss function is less than or equal to a first preset threshold, the difference between two adjacent groups of loss values is greater than zero, and the difference between two adjacent groups of loss values is less than a second preset threshold.

6. The MST electrical stimulation amount determination method according to claim 5, wherein The target stimulation amount output by the electrical stimulation amount generation model includes current intensity, stimulation frequency, pulse width, and stimulation time, and the loss function is: Among them, represents the amount of electrical stimulation predicted by the model for the i-th sample; y i represents the actual amount of electrical stimulation for the i-th sample; n represents the total number of samples; θ j represents the over-stimulation threshold of the j-th parameter of the amount of electrical stimulation; k j represents the penalty coefficient for the j-th parameter of the amount of electrical stimulation; m represents the number of parameters of the amount of electrical stimulation; represents the value of the j-th parameter in the amount of electrical stimulation predicted by the model for the i-th sample; x ij represents the j-th feature in the input data vector of the i-th sample, u j represents the mean of the j-th feature among all samples, σ j represents the standard deviation of the j-th feature among all samples, r i represents the risk coefficient for the j-th feature; p represents the number of features of the input sample data; α, β represent trade-off coefficients.

7. The MST electrical stimulation amount determination method according to claim 6, characterized in that, The optimization objective function is: J = L zo + γ * ‖ω‖ 2 ; Where ω represents the weight vector of the model, and γ represents the regularization coefficient.

8. MST electrical stimulation amount determination device, characterized in that It includes: An acquisition unit: used to acquire the basic identity data, physiological parameter data, medical record data, and electrical stimulation application indications of the target stimulated user; A calculation unit: used to input the basic identity data, the physiological parameter data, the medical record data, and the electrical stimulation application indications into an electrical stimulation amount generation model to obtain the target stimulation amount output by the electrical stimulation amount generation model; the electrical stimulation amount generation model is trained by sample influence data and its corresponding stimulation amount label results; An output unit: used to emit electrical stimulation to the target stimulated user based on the target stimulation amount.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the MST electrical stimulation amount determination method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the MST electrical stimulation amount determination method according to any one of claims 1 to 7.

Images