Method for evaluating curative effect of balance needle therapy in diabetic peripheral neuropathy

Abstract

The invention discloses a curative effect evaluation method of balance needle therapy in diabetic peripheral neuropathy, and relates to the technical field of curative effect evaluation. Constructing a medical history tree diagram of the diabetic patient, obtaining medical history influence factors of the diabetic patient, constructing a physical sign change curve of the diabetic patient, obtaining change coefficients of different time nodes, generating a change coefficient set, and inputting the change coefficient set into a curative effect judgment model to obtain effective interval duration of the balance needle therapy, acquiring fluctuation values of different real-time parameters to judge whether abnormal real-time parameters exist or not, generating a curative effect evaluation set, acquiring single evaluation coefficients of different physical sign parameters, and generating a comprehensive evaluation coefficient and a curative effect evaluation result thereof; through the technical scheme of the invention, the pertinence, accuracy and comprehensiveness of the balance needle therapy for evaluating the curative effect of the diabetic peripheral neuropathy can be obviously improved.

Description

Technical Field

[0001] The present invention relates to the technical field of efficacy evaluation, and in particular to a method for evaluating the efficacy of balanced acupuncture therapy in diabetic peripheral neuropathy. Background Art

[0002] Balanced acupuncture therapy is a new acupuncture technique that inherits traditional acupuncture techniques and innovatively integrates the brain center regulation theory of modern medicine. Its core concept is to activate the self-repair system of the brain center by acupuncture of peripheral nerve targets, thereby quickly treating diseases.

[0003] The efficacy evaluation method of balanced acupuncture therapy in diabetic peripheral neuropathy is mainly based on the improvement of patients' clinical symptoms, nerve function evaluation and possible objective examination indicators. There are many influencing factors in the efficacy evaluation of balanced acupuncture therapy, resulting in the final evaluation results often failing to reflect the actual effect of balanced acupuncture therapy.

[0004] First, different patients often have different therapeutic responses to the same therapy due to their own medical history and physical fitness. Second, the efficacy evaluation needs to be judged based on the specific effective time and expiration time of the therapy, but there is currently a lack of technical means to accurately obtain the effective time and expiration time of balanced acupuncture therapy, resulting in inaccurate evaluation results. Third, abnormal data may occasionally appear in the monitoring of patient vital sign parameters, which may also affect the results of the efficacy evaluation. In view of the deficiencies in the prior art, the present invention provides a method for evaluating the efficacy of balanced acupuncture therapy in diabetic peripheral neuropathy. Summary of the invention

[0005] The purpose of the present invention is to provide a method for evaluating the efficacy of balanced acupuncture therapy in diabetic peripheral neuropathy.

[0006] The purpose of the present invention can be achieved by the following technical solution: A method for evaluating the efficacy of balanced acupuncture therapy in diabetic peripheral neuropathy, comprising the following steps:

[0007] Step S1: collecting medical history information of diabetic patients, constructing a medical history tree diagram of diabetic patients according to the collected medical history information, and obtaining medical history influencing factors of diabetic patients according to the constructed medical history tree diagram;

[0008] Step S2: monitor the physical sign parameters of the diabetic patients before and after the balanced acupuncture therapy, construct a corresponding physical sign change curve according to the monitored physical sign parameters, obtain the change coefficients of different time nodes in the physical sign change curve, generate a set of change coefficients in combination with the medical history influencing factors, input the obtained set of change coefficients into a preset efficacy judgment model, and generate the effective interval duration of the balanced acupuncture therapy;

[0009] Step S3: Obtain the fluctuation values ​​of different vital sign parameters, determine whether there are abnormal real-time parameters, generate a therapeutic effect evaluation set based on the abnormal real-time parameters, obtain a single evaluation coefficient of different vital sign parameters based on the obtained therapeutic effect evaluation set, and generate a comprehensive evaluation coefficient of balanced acupuncture therapy and its therapeutic effect evaluation result.

[0010] Furthermore, the medical history information of the diabetic patient is collected, and the process of constructing a medical history tree diagram of the diabetic patient according to the collected medical history information includes:

[0011] The medical history information includes personal information, current medical history, past medical history, family medical history, and treatment history;

[0012] The personal information of diabetic patients is used as the first-level node of the medical history tree diagram, and the second-level nodes of the medical history tree diagram are constructed with the current medical history, past medical history, family medical history, and treatment history respectively;

[0013] The third-level nodes of the medical history tree diagram are constructed according to the medical history information corresponding to each second-level node.

[0014] Furthermore, the process of obtaining the medical history influencing factors of the diabetic patient according to the constructed medical history tree diagram includes:

[0015] Preset node weights for nodes at each level in the medical history tree diagram, including primary weight, secondary weight, and tertiary weight;

[0016] The number of nodes at each level in the medical history dendrogram is obtained, including the first-level number, the second-level number, and the third-level number, and the medical history influencing factors of diabetic patients are obtained according to the node weight and the number of nodes.

[0017] Furthermore, the process of monitoring the physical sign parameters of the diabetic patient before and after the balanced acupuncture therapy and constructing a corresponding physical sign change curve according to the monitored physical sign parameters includes:

[0018] The physical sign parameters include real-time parameters of various physical sign information of diabetic patients before and after a single balanced acupuncture treatment, and the physical sign information is divided into blood sugar index content and nerve conduction velocity;

[0019] According to the vital sign parameters, a vital sign change curve is constructed with the horizontal axis as the time node and the vertical axis as the real-time parameter. The coordinate points corresponding to the real-time parameters of adjacent time nodes are connected by a smooth curve. The vital sign change curves of different vital sign information are independent of each other.

[0020] Furthermore, the process of obtaining the change coefficients at different time nodes in the physical sign change curve and generating a set of change coefficients in combination with the medical history influencing factors includes:

[0021] Obtain parameter change points at each time node in a single vital sign change curve, construct parameter auxiliary lines for the parameter change points respectively, and use the angle between the parameter auxiliary line and the x-axis of the vital sign change curve as the change coefficient of the corresponding time node;

[0022] The ratio of the change coefficient of each time node to the medical history influencing factor of the diabetic patient is incorporated into the change coefficient set of the physical sign change curve, and the change coefficient sets of different physical sign change curves are obtained respectively.

[0023] Furthermore, the obtained set of variation coefficients is input into a preset efficacy determination model, and the process of obtaining the effective interval duration of the balanced acupuncture therapy includes:

[0024] The preset process of the efficacy determination model is as follows:

[0025] Obtain a historical change coefficient set of a single vital sign change curve, and divide it into a training set and a test set, wherein the historical change coefficient set includes change coefficient feature data and its effective interval duration;

[0026] The variation coefficient characteristic data includes the time nodes and real-time parameters corresponding to each variation coefficient in the physical sign variation curve. The effective interval duration refers to the effective time node and the invalid time node of the balance acupuncture therapy and the time interval therebetween. The initial effective time node and the invalid time node are provided by relevant personnel according to the corresponding physical sign variation curve.

[0027] Constructing a recurrent neural network, taking the coefficient of variation characteristic data and the effective interval duration in the training set as the input data and output data of the recurrent neural network respectively, and training the recurrent neural network to obtain an initial recurrent neural network;

[0028] The initial recurrent neural network is model verified using the test set, and the initial recurrent neural network with an output value less than or equal to a preset test error threshold is used as the preset efficacy determination model;

[0029] Obtain the efficacy determination model for different vital sign parameters, input each group of change coefficient sets into the corresponding efficacy determination model, obtain the effective interval duration of balanced acupuncture therapy for different vital sign parameters, feed back the effective time nodes and invalid time nodes in the effective interval duration to the corresponding historical change coefficient set, and the subsequent effective time nodes and invalid time nodes are provided by the efficacy determination model.

[0030] Furthermore, the fluctuation values ​​of different vital sign parameters are obtained to determine whether there are abnormal real-time parameters, and the process of generating a therapeutic effect evaluation set according to the abnormal real-time parameters includes:

[0031] Obtain the fluctuation value of each real-time parameter under a single vital sign parameter, set a fluctuation threshold, and compare the fluctuation value with the fluctuation threshold to determine whether there is an abnormal real-time parameter;

[0032] In the variation coefficient set corresponding to the sign change curve of the sign parameter, the variation coefficient corresponding to the abnormal real-time parameter is deleted to obtain a therapeutic effect evaluation set, and a therapeutic effect evaluation set of different sign parameters is obtained.

[0033] Furthermore, the process of obtaining a single evaluation coefficient of different physical sign parameters according to the obtained efficacy evaluation set and generating a comprehensive evaluation coefficient of the balancing acupuncture therapy and its efficacy evaluation result includes:

[0034] According to the effective interval duration of the physical sign parameter corresponding to the single efficacy evaluation set, combined with the various coefficients of variation in the efficacy evaluation set, a single evaluation coefficient G of the physical sign parameter is obtained;

[0035]

[0036] Among them, β is the preset correction coefficient, T is the effective interval duration of the balanced acupuncture therapy for the physical sign parameter, R is the influencing factor of the medical history of the diabetic patient, and D j is the coefficient of variation in the efficacy evaluation set, j = 1, 2, ..., m;

[0037] Obtain the single evaluation coefficients of different physical sign parameters, and use the average of each single evaluation coefficient as the comprehensive evaluation coefficient of balanced acupuncture therapy for diabetic patients;

[0038] An evaluation coefficient standard is set, and the comprehensive evaluation coefficient is compared with the evaluation coefficient standard to obtain an evaluation result of the efficacy of balanced acupuncture therapy for diabetic patients, wherein the evaluation result includes a good efficacy and a fair efficacy.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] 1. The present invention constructs a medical history tree diagram of diabetic patients, thereby obtaining the medical history influencing factors of different diabetic patients, and can quantify the influence of patients with different medical histories on the efficacy of the same therapy, which can significantly improve the pertinence of the efficacy evaluation for different diabetic patients;

[0041] 2. The present invention constructs a curve of changes in the physical signs of diabetic patients before and after the balanced acupuncture therapy, and then obtains the coefficient of change at different time nodes. Combining the medical history influencing factors and the efficacy determination model, the effective interval duration of the therapy for the patient can be accurately obtained, thereby avoiding the inaccuracy of the efficacy evaluation results caused by the inaccurate determination of the duration of the efficacy. It can accurately determine when the therapy is effective and when it is ineffective for different physical sign parameters, and can significantly improve the accuracy of the efficacy evaluation;

[0042] 3. The present invention can effectively avoid the influence of erroneous monitoring data on the efficacy evaluation by judging whether there are abnormal real-time parameters and not taking the abnormal real-time parameters as the basis for efficacy evaluation. By separately obtaining and combining the evaluation effects of different vital sign parameters, the comprehensiveness of the efficacy evaluation of balanced acupuncture therapy can be significantly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0044] like Figure 1 As shown, the method for evaluating the efficacy of balanced acupuncture therapy in diabetic peripheral neuropathy includes the following steps:

[0045] Step S1: collecting medical history information of diabetic patients, constructing a medical history tree diagram of diabetic patients according to the collected medical history information, and obtaining medical history influencing factors of diabetic patients according to the constructed medical history tree diagram;

[0046] Step S2: monitor the physical sign parameters of the diabetic patients before and after the balanced acupuncture therapy, construct a corresponding physical sign change curve according to the monitored physical sign parameters, obtain the change coefficients of different time nodes in the physical sign change curve, generate a set of change coefficients in combination with the medical history influencing factors, input the obtained set of change coefficients into a preset efficacy judgment model, and obtain the effective interval duration of the balanced acupuncture therapy;

[0047] Step S3: Obtain the fluctuation values ​​of different vital sign parameters, determine whether there are abnormal real-time parameters, generate a therapeutic effect evaluation set based on the abnormal real-time parameters, obtain a single evaluation coefficient of different vital sign parameters based on the obtained therapeutic effect evaluation set, and generate a comprehensive evaluation coefficient of balanced acupuncture therapy and its therapeutic effect evaluation result.

[0048] It should be further explained that, in the specific implementation process, the medical history information of the diabetic patient is collected, and the process of constructing the medical history tree diagram of the diabetic patient according to the collected medical history information includes:

[0049] The medical history information refers to the comprehensive records of the diabetes patient from the onset to the current treatment process, including:

[0050] Personal information, such as name, gender, age, occupation, contact information;

[0051] History of current illness, including a record of symptom onset, aggravating factors, and relief patterns;

[0052] Past medical history, record whether the diabetic patient has had other diseases in the past, such as hypertension, coronary heart disease, and kidney disease;

[0053] Family medical history, recording whether there are any family members of the diabetic patient with diabetes or other genetic diseases;

[0054] Treatment history, recording the previous hypoglycemic treatment plans of diabetic patients, including the types and dosages of oral hypoglycemic drugs and the use of insulin;

[0055] The medical history tree diagram is used to reflect the hierarchical relationship and logical structure within the medical history information of diabetic patients, and its construction process is as follows:

[0056] The personal information of diabetic patients is used as the first-level node of the medical history tree diagram, and the second-level nodes of the medical history tree diagram are constructed with the current medical history, past medical history, family medical history, and treatment history respectively;

[0057] Specifically, if the diabetic patient has a current medical history, then the corresponding secondary node is constructed; if not, then it is not constructed, and so on;

[0058] Constructing the third-level nodes of the medical history tree diagram according to the medical history information corresponding to each second-level node. Specifically, for the current medical history, when it contains an onset record, a third-level node is constructed, and for the past medical history, when it contains another disease, a third-level node is constructed;

[0059] For family medical history, when it contains a record of a member, a third-level node is constructed; for treatment medical history, when it contains a record of the use of an oral hypoglycemic drug or an insulin, a third-level node is constructed.

[0060] It should be further explained that, in the specific implementation process, the process of obtaining the medical history influencing factors of diabetic patients according to the constructed medical history tree diagram includes:

[0061] The corresponding node weights are preset for each level of nodes in the constructed medical history tree diagram, including primary weight, secondary weight, and tertiary weight, and are marked as Q1, Q2, and Q3 respectively. Take the medical history tree diagram of any diabetic patient as an example;

[0062] Obtain the number of nodes at each level in the medical history dendrogram of the diabetic patient, including the first-level number, the second-level number, and the third-level number, and mark them as S1, S2, and S3 respectively. Obtain the medical history influence factor of the diabetic patient according to the node weight and the number of nodes, and record it as R;

[0063]

[0064] The same method is adopted to construct the medical history dendrograms of different diabetic patients, and obtain their corresponding medical history influencing factors respectively. The medical history influencing factors can correct the influence of the efficacy of diabetic patients with different medical history information under balanced acupuncture therapy.

[0065] It should be further explained that, in the specific implementation process, the physical sign parameters of the diabetic patients before and after the balanced acupuncture therapy are monitored, and the process of constructing the corresponding physical sign change curve according to the monitored physical sign parameters includes:

[0066] The physical sign parameters refer to the real-time parameters of various physical sign information of diabetic patients before and after a single balanced acupuncture treatment. The physical sign information is divided into two aspects:

[0067] Blood glucose indexes, including FBG, 2hPBG, and HbA1c;

[0068] Nerve conduction velocity, including motor nerve conduction velocity (MCV) and sensory nerve conduction velocity (SCV) of the median nerve, common peroneal nerve, and posterior tibial nerve;

[0069] Constructing physical sign change curves of various physical sign information according to the monitored physical sign parameters, the physical sign change curves of different physical sign information are independent of each other, and the number of constructed physical sign change curves is the same as the number of physical sign information types;

[0070] The horizontal coordinate of the vital sign change curve is the time node, and the vertical coordinate is the real-time parameter corresponding to different time nodes. The coordinate points corresponding to the real-time parameters of adjacent time nodes are connected by a smooth curve. The vital sign change curve is a mathematically continuous and differentiable curve.

[0071] It should be further explained that, in the specific implementation process, the process of obtaining the change coefficients at different time nodes in the physical sign change curve and generating a set of change coefficients in combination with the medical history influencing factors includes:

[0072] Taking any vital sign change curve as an example, within the vital sign change curve, the coordinate points corresponding to the real-time parameters at each time node are marked as parameter change points;

[0073] Taking any parameter change point as an example, construct the tangent line of the parameter change point and mark it as a parameter auxiliary line, wherein the parameter auxiliary line intersects with the x-axis and the y-axis of the vital sign change curve respectively;

[0074] The angle value between the parameter auxiliary line and the x-axis of the vital sign change curve is obtained, and the angle value is an acute angle. The obtained angle value is marked as the change coefficient of the parameter change point. The parameter auxiliary line of each parameter change point is obtained by the same method, and the change coefficient of each parameter change point is obtained, that is, the change coefficient of each time node;

[0075] The obtained coefficients of change at different time nodes are numbered in chronological order and recorded as B i , where i = 1, 2, ..., n, where n is the number of time nodes, and the variation coefficients are B1, B2, ..., B n ;

[0076] According to the variation coefficients at different time nodes and the medical history influencing factors of diabetic patients, the variation coefficient set of the physical sign variation curve is obtained, and the ratio of each variation coefficient to the medical history influencing factor is included in the corresponding variation coefficient set. The variation coefficient set is {B1 / R, B2 / R, ..., B n / R}, and adopt the same method to obtain the set of variation coefficients of the physical sign parameters corresponding to different physical sign variation curves.

[0077] It should be further explained that, in the specific implementation process, the obtained set of variation coefficients is input into the preset efficacy determination model, and the process of obtaining the effective interval duration of the balanced acupuncture therapy includes:

[0078] The preset process of the efficacy determination model is as follows:

[0079] Obtain a historical change coefficient set of a single vital sign parameter, and divide the historical change coefficient set into a training set and a test set, wherein the historical change coefficient set only includes the change coefficient characteristic data of the single vital sign parameter and its corresponding effective interval duration;

[0080] The variation coefficient characteristic data includes the time node and real-time parameter corresponding to the i-th variation coefficient in the physical sign variation curve of the single physical sign parameter, and the effective interval duration refers to the effective time node and the invalid time node of the balancing acupuncture therapy and the time interval between the two;

[0081] The effective time node refers to the time node when the balanced acupuncture therapy takes effect on the single vital sign parameter, and the ineffective time node refers to the time node when the balanced acupuncture therapy takes effect on the single vital sign parameter;

[0082] The initial effective time node and expiration time node are provided by relevant personnel based on the corresponding physical sign change curve, and the subsequent effective time node and expiration time node are provided by the efficacy judgment model;

[0083] Construct a recurrent neural network, use the coefficient of variation feature data in the training set as input data of the recurrent neural network, use the effective interval duration in the training set as output data of the recurrent neural network, and train the recurrent neural network to obtain a corresponding initial recurrent neural network;

[0084] The initial recurrent neural network is model verified using the test set, and the initial recurrent neural network with an output value less than or equal to the preset test error threshold is used as the preset efficacy determination model. The same method is used to obtain efficacy determination models for different physical sign parameters;

[0085] The obtained sets of variation coefficients are respectively input into the corresponding efficacy judgment model to obtain the effective interval duration of balanced acupuncture therapy for different vital sign parameters, and the effective time nodes and failure time nodes in the obtained effective interval duration are provided to the corresponding historical variation coefficient set, so as to continuously train and test the efficacy judgment model.

[0086] It should be further explained that, in the specific implementation process, the fluctuation values ​​of different vital sign parameters are obtained, and it is determined whether there are abnormal real-time parameters. The process of generating a therapeutic effect evaluation set according to the abnormal real-time parameters includes:

[0087] Taking a single vital sign parameter as an example, the real-time parameters at different time nodes are numbered in chronological order and recorded as C i , where i = 1, 2, ..., n, where n is the number of time nodes, and the real-time parameters are C1, C2, ..., C n , obtain the fluctuation value of each real-time parameter, denoted as P i ;

[0088]

[0089] Set the fluctuation threshold P0, compare the obtained fluctuation value with the fluctuation threshold, if P i >P0, the real-time parameter corresponding to the fluctuation value is marked as an abnormal real-time parameter. i ≤P0, the real-time parameter corresponding to the fluctuation value is marked as a normal real-time parameter;

[0090] In the variation coefficient set of the single vital sign parameter, the variation coefficient corresponding to the abnormal real-time parameter is deleted to obtain the corresponding efficacy evaluation set, and the variation coefficients in the efficacy evaluation set are renumbered and recorded as D j , where j = 1, 2, ..., m, where m is the number of coefficients of variation in the efficacy evaluation set, the efficacy evaluation set being {D1, D2, ..., D m};

[0091] The same method is adopted to obtain the fluctuation values ​​of different vital sign parameters, and the abnormal real-time parameters thereof are obtained respectively, and then the efficacy evaluation set of different vital sign parameters is obtained.

[0092] It should be further explained that, in the specific implementation process, the process of obtaining a single evaluation coefficient of different physical sign parameters according to the obtained efficacy evaluation set and generating a comprehensive evaluation coefficient of the balanced acupuncture therapy and its efficacy evaluation result includes:

[0093] Taking any efficacy evaluation set as an example, the effective interval duration of the physical sign parameter corresponding to the efficacy evaluation set is obtained, and a single evaluation coefficient of the physical sign parameter is obtained by combining the various change coefficients in the efficacy evaluation set, which is recorded as G;

[0094]

[0095] Wherein, β is the preset correction coefficient, T is the effective interval duration of the balanced acupuncture therapy for the physical sign parameter, and R is the influencing factor of the medical history of the diabetic patient. The same method is adopted to obtain the single evaluation coefficients of different physical sign parameters, and the average of the obtained single evaluation coefficients is used as the comprehensive evaluation coefficient of the balanced acupuncture therapy for the diabetic patient;

[0096] An evaluation coefficient standard is set, and the obtained comprehensive evaluation coefficient is compared with the set evaluation coefficient standard. If the comprehensive evaluation coefficient is greater than or equal to the evaluation coefficient standard, it is judged that the balanced acupuncture therapy is effective for the diabetic patient. If the comprehensive evaluation coefficient is less than the evaluation coefficient standard, it is judged that the balanced acupuncture therapy is generally effective for the diabetic patient. The efficacy evaluation results include good efficacy and general efficacy, and the obtained efficacy evaluation results and the comprehensive evaluation coefficient are bound together.

[0097] 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 method for evaluating the efficacy of balanced acupuncture therapy in diabetic peripheral neuropathy, characterized in that: The following steps are involved: Step S1: collecting medical history information of diabetic patients, constructing a medical history tree diagram of diabetic patients according to the collected medical history information, and obtaining medical history influencing factors of diabetic patients according to the constructed medical history tree diagram; Step S2: monitor the physical sign parameters of the diabetic patients before and after the balanced acupuncture therapy, construct a corresponding physical sign change curve according to the monitored physical sign parameters, obtain the change coefficients of different time nodes in the physical sign change curve, generate a set of change coefficients in combination with the medical history influencing factors, input the obtained set of change coefficients into a preset efficacy judgment model, and obtain the effective interval duration of the balanced acupuncture therapy; Step S3: Obtain the fluctuation values ​​of different vital sign parameters, determine whether there are abnormal real-time parameters, generate a therapeutic effect evaluation set based on the abnormal real-time parameters, obtain a single evaluation coefficient of different vital sign parameters based on the obtained therapeutic effect evaluation set, and generate a comprehensive evaluation coefficient of balanced acupuncture therapy and its therapeutic effect evaluation result.

2. The method for evaluating the efficacy of balanced acupuncture therapy in diabetic peripheral neuropathy according to claim 1, characterized in that: The process of constructing a medical history tree diagram includes: The medical history information includes personal information, current medical history, past medical history, family medical history, and treatment history; The personal information of diabetic patients is used as the first-level node of the medical history tree diagram, and the second-level nodes of the medical history tree diagram are constructed with the current medical history, past medical history, family medical history, and treatment history respectively; The third-level nodes of the medical history tree diagram are constructed according to the medical history information corresponding to each second-level node.

3. The method for evaluating the efficacy of balanced acupuncture therapy in diabetic peripheral neuropathy according to claim 2, characterized in that: The process of obtaining the medical history influencing factors based on the medical history tree diagram includes: Preset node weights for nodes at each level in the medical history tree diagram, including primary weight, secondary weight, and tertiary weight; The number of nodes at each level in the medical history dendrogram is obtained, including the first-level number, the second-level number, and the third-level number, and the medical history influencing factors of diabetic patients are obtained according to the node weight and the number of nodes.

4. The method for evaluating the efficacy of balanced acupuncture therapy in diabetic peripheral neuropathy according to claim 3, characterized in that: The process of constructing the physical sign change curve includes: The physical sign parameters include real-time parameters of various physical sign information of diabetic patients before and after a single balanced acupuncture treatment, and the physical sign information is divided into blood sugar index content and nerve conduction velocity; According to the vital sign parameters, a vital sign change curve is constructed with the horizontal axis as the time node and the vertical axis as the real-time parameter. The coordinate points corresponding to the real-time parameters of adjacent time nodes are connected by a smooth curve. The vital sign change curves of different vital sign information are independent of each other.

5. The method for evaluating the efficacy of balanced acupuncture therapy in diabetic peripheral neuropathy according to claim 4, characterized in that: The process of generating a set of coefficients of variation includes: Obtain parameter change points at each time node in a single vital sign change curve, construct parameter auxiliary lines for the parameter change points respectively, and use the angle between the parameter auxiliary line and the x-axis of the vital sign change curve as the change coefficient of the corresponding time node; The ratio of the change coefficient of each time node to the medical history influencing factor of the diabetic patient is incorporated into the change coefficient set of the physical sign change curve, and the change coefficient sets of different physical sign change curves are obtained respectively.

6. The method for evaluating the efficacy of balanced acupuncture therapy in diabetic peripheral neuropathy according to claim 5, characterized in that: The preset process of the efficacy determination model is as follows: Obtain a historical change coefficient set of a single vital sign change curve, and divide it into a training set and a test set, wherein the historical change coefficient set includes change coefficient feature data and its effective interval duration; The variation coefficient characteristic data includes the time nodes and real-time parameters corresponding to each variation coefficient in the physical sign variation curve. The effective interval duration refers to the effective time node and the invalid time node of the balance acupuncture therapy and the time interval therebetween. The initial effective time node and the invalid time node are provided by relevant personnel according to the corresponding physical sign variation curve. Constructing a recurrent neural network, taking the coefficient of variation characteristic data and the effective interval duration in the training set as the input data and output data of the recurrent neural network respectively, and training the recurrent neural network to obtain an initial recurrent neural network; The initial recurrent neural network is model verified using the test set, and the initial recurrent neural network with an output value less than or equal to a preset test error threshold is used as the preset efficacy determination model; Obtain the efficacy determination model for different vital sign parameters, input each group of change coefficient sets into the corresponding efficacy determination model, obtain the effective interval duration of balanced acupuncture therapy for different vital sign parameters, feed back the effective time nodes and invalid time nodes in the effective interval duration to the corresponding historical change coefficient set, and the subsequent effective time nodes and invalid time nodes are provided by the efficacy determination model.

7. The method for evaluating the efficacy of balanced acupuncture therapy in diabetic peripheral neuropathy according to claim 6, characterized in that: The process of determining abnormal real-time parameters and generating a therapeutic effect evaluation set includes: Obtain the fluctuation value of each real-time parameter under a single vital sign parameter, set a fluctuation threshold, and compare the fluctuation value with the fluctuation threshold to determine whether there is an abnormal real-time parameter; In the variation coefficient set corresponding to the sign change curve of the sign parameter, the variation coefficient corresponding to the abnormal real-time parameter is deleted to obtain a therapeutic effect evaluation set, and a therapeutic effect evaluation set of different sign parameters is obtained.

8. The method for evaluating the efficacy of balanced acupuncture therapy in diabetic peripheral neuropathy according to claim 7, characterized in that: The process of generating the comprehensive evaluation coefficient and its efficacy evaluation results includes: According to the effective interval duration of the physical sign parameter corresponding to the single efficacy evaluation set, combined with the various coefficients of variation in the efficacy evaluation set, a single evaluation coefficient G of the physical sign parameter is obtained; Among them, β is the preset correction coefficient, T is the effective interval duration of the balanced acupuncture therapy for the physical sign parameter, R is the influencing factor of the medical history of the diabetic patient, and D j is the coefficient of variation in the efficacy evaluation set, j = 1, 2, ..., m; Obtain the single evaluation coefficients of different physical sign parameters, and use the average of each single evaluation coefficient as the comprehensive evaluation coefficient of balanced acupuncture therapy for diabetic patients; An evaluation coefficient standard is set, and the comprehensive evaluation coefficient is compared with the evaluation coefficient standard to obtain an evaluation result of the efficacy of balanced acupuncture therapy for diabetic patients, wherein the evaluation result includes a good efficacy and a fair efficacy.

Images