Deep learning-based knee osteoarthritis acupuncture efficacy prediction system

Abstract

The present application relates to the technical field of medical data processing, in particular to a knee osteoarthritis acupuncture efficacy prediction system based on deep learning. The system obtains acupuncture treatment parameters and acupuncture effect parameters of historical knee osteoarthritis patients; based on the acupuncture effect parameters, the historical knee osteoarthritis patients are divided into patient categories, the contribution degree is obtained according to the distribution of each acupuncture treatment parameter in each patient category and the difference from the distribution in other patient categories; the local efficacy feedback value is obtained according to the contribution degree and the acupuncture effect parameters, and then the evaluation score is obtained; the acupuncture efficacy prediction model is trained through the acupuncture treatment parameters, the evaluation score and the acupuncture effect parameters, and the trained acupuncture efficacy prediction model is obtained. The present application accurately determines the participation degree of each acupuncture treatment parameter of each historical knee osteoarthritis patient by dynamically obtaining the evaluation score, and effectively improves the accuracy of the acupuncture efficacy prediction model training.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical data processing, in particular to a knee osteoarthritis acupuncture efficacy prediction system based on deep learning. BACKGROUND

[0002] Knee osteoarthritis is a chronic degenerative disease characterized by joint cartilage degeneration, hyperostosis and synovial inflammation, mainly manifested as knee pain, stiffness and limited mobility. Acupuncture, as the core means of traditional Chinese medicine therapy, can regulate local blood and relieve inflammation by stimulating specific acupoints. It has been confirmed by many clinical studies that it can effectively improve the pain degree and joint function of patients with knee osteoarthritis. For example, electroacupuncture stimulation of the six acupoints around the knee (such as Du'nu, Yanglingquan, etc.) can significantly reduce intra-articular pressure and promote cartilage repair. However, different acupuncture treatment parameters will have different effects on the treatment of patients with knee osteoarthritis during acupuncture treatment. Therefore, in order to effectively treat patients with knee osteoarthritis, it is necessary to accurately predict the treatment effect through acupuncture treatment parameters.

[0003] In the prior art, a large number of various acupuncture treatment parameters of historical knee osteoarthritis patients and fixed weights corresponding to various acupuncture treatment parameters and acupuncture effect parameters that can represent the treatment effect of historical knee osteoarthritis patients are used to train an acupuncture efficacy prediction model to obtain a trained acupuncture efficacy prediction model. Then, according to the various acupuncture treatment parameters of the knee osteoarthritis patient, the trained acupuncture efficacy prediction model is used to predict the acupuncture treatment effect of the knee osteoarthritis patient. However, in actual situations, the relationship between various acupuncture treatment parameters and efficacy is not fixed. For example, the analgesic effect is significant when the electroacupuncture frequency is 2-4 Hz, but when it exceeds 4 Hz, the effect may decrease due to neural adaptation. Therefore, the training of the acupuncture efficacy prediction model in the prior art is biased, which affects the accurate prediction of the acupuncture treatment effect of the knee osteoarthritis patient. SUMMARY

[0004] In order to solve the technical problem of bias in the training of the acupuncture efficacy prediction model in the prior art, the purpose of the present application is to provide a knee osteoarthritis acupuncture efficacy prediction system based on deep learning, and the technical solution adopted is as follows:

[0005] The present application provides a knee osteoarthritis acupuncture efficacy prediction system based on deep learning, which comprises the following steps:

[0006] A data acquisition module is used to acquire various acupuncture treatment parameters and acupuncture effect parameters of each historical knee osteoarthritis patient;

[0007] The contribution degree acquisition module is configured to divide the historical knee osteoarthritis patients into patient categories based on the acupuncture effect parameters, and acquire the contribution degree of each acupuncture treatment parameter in each patient category according to the distribution of each acupuncture treatment parameter in each patient category and the difference from the distribution in other patient categories.

[0008] The evaluation score acquisition module is configured to acquire an efficacy contribution curve of each acupuncture treatment parameter according to the contribution degree and the acupuncture effect parameters in each patient category, acquire a local efficacy feedback value based on the change of the efficacy contribution curve, and acquire an evaluation score of each acupuncture treatment parameter of each historical knee osteoarthritis patient according to each acupuncture treatment parameter of each historical knee osteoarthritis patient and the corresponding local efficacy feedback value.

[0009] The acupuncture efficacy prediction model acquisition module is configured to train the acupuncture efficacy prediction model by using each acupuncture treatment parameter, the evaluation score and the acupuncture effect parameter of each historical knee osteoarthritis patient, and obtain the trained acupuncture efficacy prediction model.

[0010] Further, the contribution degree acquisition method is as follows:

[0011] The compactness degree of each acupuncture treatment parameter in each patient category is acquired according to the distribution of each acupuncture treatment parameter in each patient category.

[0012] The special degree of each acupuncture treatment parameter in each patient category is acquired according to the difference and size difference of the compactness degree of each acupuncture treatment parameter in each patient category and other patient categories.

[0013] The product of the compactness degree and the special degree of each acupuncture treatment parameter in each patient category is taken as the contribution degree of each acupuncture treatment parameter in each patient category.

[0014] Further, the compactness degree acquisition method is as follows:

[0015] For any acupuncture treatment parameter and any patient category, the historical knee osteoarthritis patients in the patient category are clustered by using the DBSCAN density clustering algorithm according to the size of the acupuncture treatment parameter of each historical knee osteoarthritis patient in the patient category, and a corresponding local category of the acupuncture treatment parameter in the patient category is acquired.

[0016] The number of historical knee osteoarthritis patients in each local category is taken as a local patient number.

[0017] The ratio of the maximum local patient number to the number of all historical knee osteoarthritis patients in the patient category is taken as a reference stability degree of the acupuncture treatment parameter in the patient category.

[0018] the product of the reference stability degree and the local category number reciprocal, as the compactness degree of the acupuncture treatment parameter in the patient category.

[0019] Further, the special degree acquisition method is:

[0020] For any acupuncture treatment parameter and any patient category, acquiring the mean value of the compactness degree of the acupuncture treatment parameter in all patient categories except the patient category, as a first characteristic value;

[0021] the difference between the compactness degree of the acupuncture treatment parameter in the patient category and the first characteristic value, as the first differentiation degree of the acupuncture treatment parameter in the patient category;

[0022] acquiring the mean value of the acupuncture treatment parameter of all historical knee osteoarthritis patients in the patient category, as the overall reference value of the acupuncture treatment parameter in the patient category;

[0023] acquiring the mean value of the overall reference values of the acupuncture treatment parameter in all patient categories except the patient category, as a second characteristic value;

[0024] the difference between the overall reference value of the acupuncture treatment parameter in the patient category and the second characteristic value, as the second differentiation degree of the acupuncture treatment parameter in the patient category;

[0025] the result of normalizing the sum of the first differentiation degree and the second differentiation degree, as the special degree of the acupuncture treatment parameter in the patient category.

[0026] Further, the efficacy contribution curve acquisition method is:

[0027] the mean value of the acupuncture effect parameter of all historical knee osteoarthritis patients in each patient category, as the target effect parameter of each patient category;

[0028] For any acupuncture treatment parameter, the contribution degree of the acupuncture treatment parameter in each patient category is taken as the y value in the two-dimensional coordinate, and the target effect parameter of each patient category is taken as the x value in the two-dimensional coordinate, to acquire the reference coordinate of each patient category corresponding to the acupuncture treatment parameter.

[0029] fitting the point corresponding to the reference coordinate in the two-dimensional coordinate system into a curve, as the efficacy contribution curve of the acupuncture treatment parameter.

[0030] Further, the local efficacy feedback value acquisition method is:

[0031] For the contribution curve of the curative effect of any acupuncture treatment parameter, the extreme points on the contribution curve of the curative effect of the acupuncture treatment parameter are taken as the division points, and the contribution curve of the curative effect of the acupuncture treatment parameter is divided into a plurality of local curve segments;

[0032] For any local curve segment, the ratio of the contribution degree range size of the local curve segment to the overall contribution degree range size of the contribution curve of the curative effect of the acupuncture treatment parameter is taken as the local feedback degree of the local curve segment.

[0033] The product of the slope of the local curve segment and the local feedback degree is taken as a local curative effect feedback value of the acupuncture treatment parameter.

[0034] Further, the evaluation score acquisition method is:

[0035] For any historical knee osteoarthritis patient and any acupuncture treatment parameter, the mean value of the acupuncture treatment parameter of all historical knee osteoarthritis patients in the patient category corresponding to the maximum local curative effect feedback value of the acupuncture treatment parameter is taken as a target analysis value;

[0036] The difference between the acupuncture treatment parameter of the historical knee osteoarthritis patient and the target analysis value is taken as a first important analysis value of the acupuncture treatment parameter of the historical knee osteoarthritis patient;

[0037] The difference between the local curative effect feedback value corresponding to the patient category in which the acupuncture treatment parameter of the historical knee osteoarthritis patient is located and the maximum local curative effect feedback value of the acupuncture treatment parameter is taken as a second important analysis value of the acupuncture treatment parameter of the historical knee osteoarthritis patient;

[0038] The result of negative correlation and normalization of the sum of the first important analysis value and the second important analysis value is taken as the evaluation score of the acupuncture treatment parameter of the historical knee osteoarthritis patient.

[0039] Further, the acupuncture curative effect prediction model acquisition method is:

[0040] Each acupuncture treatment parameter of each historical knee osteoarthritis patient and the evaluation score of each acupuncture treatment parameter are taken as the input of the acupuncture curative effect prediction model, the acupuncture effect parameter of each historical knee osteoarthritis patient is taken as the output of the acupuncture curative effect prediction model, the acupuncture curative effect prediction model is trained, and a trained acupuncture curative effect prediction model is obtained.

[0041] Further, the patient category acquisition method is:

[0042] The historical knee osteoarthritis patients are clustered by the DBSCAN density clustering algorithm according to the acupuncture effect parameter of each historical knee osteoarthritis patient, and the patient categories are obtained.

[0043] Further, the acupuncture effect parameter is a treatment effect score of a doctor according to each historical knee osteoarthritis patient after acupuncture treatment.

[0044] The present application has the following beneficial effects:

[0045] The present application first divides the historical knee osteoarthritis patients into patient categories based on the acupuncture effect parameter, which is conducive to subsequent efficient analysis of the treatment effect of each acupuncture treatment parameter on knee osteoarthritis; in order to analyze the influence of each acupuncture treatment parameter on the acupuncture treatment effect, the contribution degree of each acupuncture treatment parameter in each patient category is obtained according to the distribution of each acupuncture treatment parameter in each patient category and the difference from the distribution in other patient categories, which accurately reflects the influence degree of each patient category corresponding to each acupuncture treatment parameter range on the acupuncture treatment effect; then, the efficacy contribution curve of each acupuncture treatment parameter is obtained according to the contribution degree and the acupuncture effect parameter in each patient category, which accurately reflects the feedback of each acupuncture treatment parameter on the acupuncture treatment effect, so that the reference degree corresponding to each acupuncture treatment parameter of each historical knee osteoarthritis patient can be accurately analyzed subsequently; then, the local efficacy feedback value is obtained based on the change of the efficacy contribution curve, which accurately reflects the influence of each acupuncture treatment parameter on each stage of the acupuncture treatment effect, and then the evaluation score of each acupuncture treatment parameter of each historical knee osteoarthritis patient is dynamically obtained according to each acupuncture treatment parameter of each historical knee osteoarthritis patient and the corresponding local efficacy feedback value, which accurately reflects the effective weight of each acupuncture treatment parameter of each historical knee osteoarthritis patient on the acupuncture effect parameter; therefore, by using each acupuncture treatment parameter, evaluation score and acupuncture effect parameter of each historical knee osteoarthritis patient, the acupuncture efficacy prediction model is trained, the trained acupuncture efficacy prediction model is accurately obtained, the accuracy of the acupuncture efficacy prediction model in predicting the acupuncture treatment effect of the knee osteoarthritis patient is effectively improved, which is conducive to helping the doctor to further optimize the acupuncture treatment scheme for the knee osteoarthritis patient and improve the pertinence and effectiveness of the acupuncture treatment, so as to achieve better acupuncture treatment effect and improve the treatment satisfaction of the knee osteoarthritis patient. BRIEF DESCRIPTION OF DRAWINGS

[0046] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0047] Figure 1A structural block diagram of a knee osteoarthritis acupuncture efficacy prediction system based on deep learning provided by an embodiment of the present application is shown in FIG. 1.

[0048] Figure 2 A flowchart of a contribution degree acquisition method provided by an embodiment of the present application is shown in FIG. 6.

[0049] Figure 3 A schematic diagram of a computer device provided by an embodiment of the present application is shown in FIG. 7. DETAILED DESCRIPTION

[0050] In order to further illustrate the technical means and effects taken by the present application to achieve the predetermined purposes, the specific embodiments, structures, features and effects of the knee osteoarthritis acupuncture efficacy prediction system based on deep learning provided by the present application are described in detail as follows in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0052] The specific scheme of the knee osteoarthritis acupuncture efficacy prediction system based on deep learning provided by the present application is described in detail below in combination with the accompanying drawings.

[0053] Embodiment 1

[0054] The present application provides a knee osteoarthritis acupuncture efficacy prediction system based on deep learning, which is shown in FIG. 1. Figure 1 The structural block diagram of the knee osteoarthritis acupuncture efficacy prediction system based on deep learning provided by the embodiment of the present application is shown in FIG. 1, which includes a data acquisition module 10, a contribution degree acquisition module 20, an evaluation score acquisition module 30 and an acupuncture efficacy prediction model acquisition module 40.

[0055] The data acquisition module 10 is used to acquire various acupuncture treatment parameters and acupuncture effect parameters of each historical knee osteoarthritis patient.

[0056] Specifically, information of a preset number of historical knee osteoarthritis patients is acquired through a hospital database, including various acupuncture treatment parameters and acupuncture effect parameters of each historical knee osteoarthritis patient. The acupuncture effect parameters are scores of treatment effect of each historical knee osteoarthritis patient after acupuncture treatment by a doctor, and the acupuncture treatment parameters include various information such as electric acupuncture frequency, electric acupuncture depth, and characteristic information of the historical knee osteoarthritis patient that affects the acupuncture treatment effect, such as age (age affects the acupuncture treatment effect) and the like. The preset number is set to 10,000 in this embodiment, and the range of the acupuncture effect parameters is 0 to 10. The implementer can set the preset number and the range of the acupuncture effect parameters according to the actual situation, which is not limited herein.

[0057] It should be noted that the acupuncture treatment parameters that are not numerical values need to be converted into numerical values by encoding to ensure that all the acupuncture treatment parameters that appear later are in numerical format. The method of converting non-numerical values into numerical values is a known technology and will not be described in detail.

[0058] The contribution degree acquisition module 20 is configured to divide the historical knee osteoarthritis patients into patient categories based on the acupuncture effect parameters, and to acquire the contribution degree of each acupuncture treatment parameter in each patient category according to the distribution of each acupuncture treatment parameter in each patient category and the difference from the distribution in other patient categories.

[0059] Specifically, since the various acupuncture treatment parameters of different historical knee osteoarthritis patients are different, the acupuncture treatment effects of different historical knee osteoarthritis patients are different. In order to better analyze the influence of each acupuncture treatment parameter on the acupuncture treatment effect, the historical knee osteoarthritis patients are first divided into patient categories based on the acupuncture effect parameters in this embodiment. It should be noted that the acupuncture treatment effects of the historical knee osteoarthritis patients in the same patient category are similar. In this embodiment, the historical knee osteoarthritis patients are clustered according to the acupuncture effect parameters of each historical knee osteoarthritis patient by the DBSCAN density clustering algorithm to obtain the patient categories. The DBSCAN density clustering algorithm is a known technology and will not be described in detail.

[0060] The more concentrated the distribution of a certain acupuncture treatment parameter of historical knee osteoarthritis patients in a certain patient category is, the greater the impact of the acupuncture treatment parameter on the treatment effect of the historical knee osteoarthritis patients in the patient category should be. The more dispersed the distribution of the acupuncture treatment parameter of the historical knee osteoarthritis patients in the patient category is, the smaller the impact of the acupuncture treatment parameter on the treatment effect of the historical knee osteoarthritis patients in the patient category can be. On the other hand, when the distribution of a certain acupuncture treatment parameter in a certain patient category is significantly different from the distribution in other patient categories, the acupuncture treatment parameter is more specific in the patient category, which indirectly indicates that the acupuncture treatment parameter can have a greater impact on the treatment effect of the historical knee osteoarthritis patients in the patient category. Further, the embodiment obtains the contribution degree of each acupuncture treatment parameter in each patient category according to the distribution of each acupuncture treatment parameter in each patient category and the difference from the distribution in other patient categories. The greater the contribution degree is, the greater the impact of the corresponding acupuncture treatment parameter on the treatment effect of the historical knee osteoarthritis patients in the corresponding patient category is.

[0061] Preferably, in one implementation manner of the embodiment, the contribution degree acquisition method can refer to Figure 2 which shows a flowchart of a contribution degree acquisition method provided by the embodiment. The method comprises the following steps:

[0062] Step S201: According to the distribution of each acupuncture treatment parameter in each patient category, obtain the compactness degree of each acupuncture treatment parameter in each patient category.

[0063] The more equal the acupuncture treatment parameter of historical knee osteoarthritis patients in a certain patient category is, the more compact the distribution of the acupuncture treatment parameter in the patient category is. Further, the embodiment obtains the compactness degree of each acupuncture treatment parameter in each patient category according to the distribution of each acupuncture treatment parameter in each patient category. The greater the compactness degree is, the greater the impact of the corresponding acupuncture treatment parameter on the treatment effect of the historical knee osteoarthritis patients in the corresponding patient category can be.

[0064] In an implementable manner of the embodiment, the compactness obtaining method is as follows: for any kind of acupuncture treatment parameter and any patient category, the historical knee osteoarthritis patients in the patient category are clustered according to the size of the kind of acupuncture treatment parameter of each historical knee osteoarthritis patient in the patient category by the DBSCAN density clustering algorithm, to obtain the corresponding local category of the kind of acupuncture treatment parameter in the patient category; the more the number of historical knee osteoarthritis patients in the local category and the fewer the number of local categories, the more compact the distribution of the kind of acupuncture treatment parameter in the patient category. Therefore, the number of historical knee osteoarthritis patients in each local category is obtained as the local patient number; then the ratio of the maximum local patient number to the number of all historical knee osteoarthritis patients in the patient category is taken as the reference stability degree of the kind of acupuncture treatment parameter in the patient category; finally, the product of the reference stability degree and the reciprocal of the number of local categories is taken as the compactness of the kind of acupuncture treatment parameter in the patient category.

[0065] Up to now, the compactness of each kind of acupuncture treatment parameter in each patient category is obtained.

[0066] Step S202: According to the compactness difference and size difference of each kind of acupuncture treatment parameter in each patient category and other patient categories, the special degree of each kind of acupuncture treatment parameter in each patient category is obtained.

[0067] When the compactness of a kind of acupuncture treatment parameter in a patient category and the compactness of the kind of acupuncture treatment parameter in other patient categories exist obvious difference, and the kind of acupuncture treatment parameter of the historical knee osteoarthritis patients in the patient category and the kind of acupuncture treatment parameter of the historical knee osteoarthritis patients in other patient categories exist obvious difference, it means that the kind of acupuncture treatment parameter is more special in the patient category. Therefore, according to the compactness difference and size difference of each kind of acupuncture treatment parameter in each patient category and other patient categories, the special degree of each kind of acupuncture treatment parameter in each patient category is obtained. The greater the special degree, the greater the influence of the corresponding kind of acupuncture treatment parameter on the treatment of the historical knee osteoarthritis patients in the corresponding patient category.

[0068] In an implementable manner of the embodiment, the special degree acquisition method is as follows: for any kind of acupuncture treatment parameter and any patient category, the mean value of the compactness degree of the kind of acupuncture treatment parameter in all patient categories except the patient category is acquired as a first characteristic value; then the absolute value of the difference between the compactness degree of the kind of acupuncture treatment parameter in the patient category and the first characteristic value is taken as a first differentiation degree of the kind of acupuncture treatment parameter in the patient category; further, the mean value of the kind of acupuncture treatment parameter of all historical knee osteoarthritis patients in the patient category is acquired as an overall reference value of the kind of acupuncture treatment parameter in the patient category; the mean value of the overall reference values of the kind of acupuncture treatment parameter in all patient categories except the patient category is acquired as a second characteristic value; then the absolute value of the difference between the overall reference value of the kind of acupuncture treatment parameter in the patient category and the second characteristic value is taken as a second differentiation degree of the kind of acupuncture treatment parameter in the patient category; when both the first differentiation degree and the second differentiation degree are greater, it indicates that the kind of acupuncture treatment parameter is more special in the patient category; and then the result of normalizing the sum of the first differentiation degree and the second differentiation degree is taken as the special degree of the kind of acupuncture treatment parameter in the patient category. In the embodiment, the sum of the first differentiation degree and the second differentiation degree is normalized by the norm normalization function.

[0069] At this point, the special degree of each kind of acupuncture treatment parameter in each patient category is acquired.

[0070] Step S203: the product of the compactness degree and the special degree of each kind of acupuncture treatment parameter in each patient category is taken as the contribution degree of each kind of acupuncture treatment parameter in each patient category.

[0071] It is known that the greater the compactness degree and the greater the special degree, the greater the influence of the corresponding kind of acupuncture treatment parameter on the treatment of the historical knee osteoarthritis patients in the corresponding patient category. Therefore, the product of the compactness degree and the special degree of each kind of acupuncture treatment parameter in each patient category is taken as the contribution degree of each kind of acupuncture treatment parameter in each patient category.

[0072] At this point, the contribution degree of each kind of acupuncture treatment parameter in each patient category is acquired.

[0073] The evaluation score acquisition module 30 is configured to acquire the efficacy contribution curve of each kind of acupuncture treatment parameter according to the contribution degree and the acupuncture effect parameter in each patient category; acquire the local efficacy feedback value based on the change of the efficacy contribution curve; and acquire the evaluation score of each kind of acupuncture treatment parameter of each historical knee osteoarthritis patient according to each kind of acupuncture treatment parameter of each historical knee osteoarthritis patient and the corresponding local efficacy feedback value.

[0074] Specifically, in the process of acupuncture treatment for knee osteoarthritis patients, each acupuncture treatment parameter has different effects on knee osteoarthritis. In order to accurately analyze the effect of each acupuncture treatment parameter on the treatment of knee osteoarthritis, each acupuncture treatment parameter is analyzed separately. First, according to the contribution degree of each acupuncture treatment parameter in each patient category and the acupuncture effect parameter in each patient category, the efficacy contribution curve of each acupuncture treatment parameter is obtained, which accurately reflects the effect of each acupuncture treatment parameter on the acupuncture treatment effect. The method for obtaining the efficacy contribution curve is as follows: the mean value of the acupuncture effect parameter of all historical knee osteoarthritis patients in each patient category is taken as the target effect parameter of each patient category; for any acupuncture treatment parameter, the contribution degree of the acupuncture treatment parameter in each patient category is taken as the y value in the two-dimensional coordinate, and the target effect parameter of each patient category is taken as the x value in the two-dimensional coordinate, to obtain the reference coordinates of each patient category corresponding to the acupuncture treatment parameter; then the point corresponding to the reference coordinates in the two-dimensional coordinate system is fitted as a curve, which is taken as the efficacy contribution curve of the acupuncture treatment parameter.

[0075] In order to analyze the effect of each acupuncture treatment parameter on the acupuncture treatment effect, and then obtain the local efficacy feedback value of each acupuncture treatment parameter based on the change of the efficacy contribution curve of each acupuncture treatment parameter. There can be multiple local efficacy feedback values for one acupuncture treatment parameter.

[0076] In an implementable manner of the embodiment, the method for obtaining the local curative effect feedback value is as follows: for the curative effect contribution curve of any acupuncture treatment parameter, the extreme points on the curative effect contribution curve of the acupuncture treatment parameter are all taken as the segmentation points, and the curative effect contribution curve of the acupuncture treatment parameter is divided into local curve segments; it should be noted that the segmentation points are taken as the termination points of the local curve segments. For any local curve segment, the greater the contribution degree range corresponding to the local curve segment is, the greater the effect of the acupuncture treatment parameter in the acupuncture effect parameter range corresponding to the local curve segment is; the greater the slope of the local curve segment is, the better the influence of the acupuncture treatment parameter on the acupuncture treatment effect in the acupuncture effect parameter range corresponding to the local curve segment is; therefore, the embodiment obtains the ratio of the contribution degree range of the local curve segment to the overall contribution degree range of the curative effect contribution curve of the acupuncture treatment parameter, as the local feedback degree of the local curve segment; then the product of the slope of the local curve segment and the local feedback degree is taken as a local curative effect feedback value of the acupuncture treatment parameter, and a local curative effect feedback value of the acupuncture treatment parameter corresponding to a local curve segment of the curative effect contribution curve of the acupuncture treatment parameter is inferred. It should be noted that the slope of the local curve segment is the slope of the straight line passing through the two points at the beginning and the end of the local curve segment; in addition, if the contribution degree range of the local curve segment is only a numerical value, the local feedback degree of the local curve segment is defaulted to be 0.

[0077] At this point, the local curative effect feedback value of each acupuncture treatment parameter is obtained. When the local curative effect feedback value is greater and greater, the positive influence of the acupuncture treatment parameter on the treatment effect in the acupuncture effect parameter range corresponding to the local curve segment is greater. When the local curative effect feedback value is 0, the acupuncture treatment parameter has no influence on the treatment effect in the acupuncture effect parameter range corresponding to the local curve segment; when the local curative effect feedback value is smaller and smaller, the adverse influence of the acupuncture treatment parameter on the treatment effect in the acupuncture effect parameter range corresponding to the local curve segment is greater. The local curative effect feedback value of each acupuncture treatment parameter accurately reflects the treatment feedback of each acupuncture treatment parameter on knee osteoarthritis.

[0078] It is known that in the prior art, a acupuncture treatment effect prediction model is trained by various acupuncture treatment parameters of historical knee osteoarthritis patients and fixed weights corresponding to various acupuncture treatment parameters and acupuncture effect parameters representing the treatment effect of the historical knee osteoarthritis patients, a trained acupuncture treatment effect prediction model is obtained, and then the acupuncture treatment effect of the knee osteoarthritis patient is predicted according to various acupuncture treatment parameters of the knee osteoarthritis patient by the trained acupuncture treatment effect prediction model. However, in actual situations, various acupuncture treatment parameters of each historical knee osteoarthritis patient are different, and when the size of a certain acupuncture treatment parameter is different, the acupuncture treatment effect produced is also different. Therefore, in the process of training the acupuncture treatment effect prediction model, the evaluation score of each acupuncture treatment parameter of each historical knee osteoarthritis patient, i.e., the reference weight, is dynamically obtained according to each acupuncture treatment parameter of each historical knee osteoarthritis patient and the corresponding local treatment effect feedback value. The larger the evaluation score, the better the acupuncture treatment effect of the corresponding acupuncture treatment parameter of the corresponding historical knee osteoarthritis patient. This is conducive to subsequent accurate training of the acupuncture treatment effect prediction model and improves the accuracy of the acupuncture treatment effect prediction model.

[0079] Preferably, in one implementation manner of the present embodiment, the evaluation score is obtained by: for any historical knee osteoarthritis patient and any acupuncture treatment parameter, the larger the acupuncture treatment parameter of the historical knee osteoarthritis patient is in the acupuncture treatment parameter range corresponding to the acupuncture effect parameter range corresponding to the maximum local treatment effect feedback value of the acupuncture treatment parameter, the better the acupuncture treatment parameter of the historical knee osteoarthritis patient is for the treatment effect of the historical knee osteoarthritis patient, and the greater the significance of the acupuncture treatment parameter of the historical knee osteoarthritis patient in analyzing the acupuncture treatment effect of the historical knee osteoarthritis patient. Further, the present embodiment takes the mean value of the acupuncture treatment parameter of all historical knee osteoarthritis patients in the patient category corresponding to the maximum local treatment effect feedback value of the acupuncture treatment parameter as the target analysis value; then takes the absolute value of the difference between the acupuncture treatment parameter of the historical knee osteoarthritis patient and the target analysis value as the first important analysis value of the acupuncture treatment parameter of the historical knee osteoarthritis patient; the smaller the first important analysis value, the more likely the acupuncture treatment parameter of the historical knee osteoarthritis patient is in the range that has a beneficial effect on the acupuncture treatment effect, and the greater the significance of the acupuncture treatment parameter of the historical knee osteoarthritis patient in analyzing the acupuncture treatment effect of the historical knee osteoarthritis patient.

[0080] To more accurately analyze the influence of the acupuncture treatment parameter of the historical knee osteoarthritis patient on the acupuncture treatment effect of the historical knee osteoarthritis patient, the difference absolute value between the local efficacy feedback value corresponding to the patient category in which the acupuncture treatment parameter of the historical knee osteoarthritis patient is located and the maximum local efficacy feedback value of the acupuncture treatment parameter is taken as a second important analysis value of the acupuncture treatment parameter of the historical knee osteoarthritis patient; the smaller the second important analysis value, the better the influence of the acupuncture treatment parameter of the historical knee osteoarthritis patient on the treatment effect, and the greater the reference degree of the acupuncture treatment parameter of the historical knee osteoarthritis patient should be; it should be noted that the essence of the change of the acupuncture treatment effect is caused by the change of the acupuncture treatment parameter, so the range of the acupuncture treatment parameter in the acupuncture effect parameter range corresponding to a certain local efficacy feedback value of the acupuncture treatment parameter is uniquely fixed, which indirectly indicates that the acupuncture treatment parameter of the historical knee osteoarthritis patient will only correspond to one local efficacy feedback value;

[0081] To accurately obtain the reference situation of the acupuncture treatment parameter of the historical knee osteoarthritis patient, and then add the first important analysis value and the second important analysis value, and then perform negative correlation and normalization on the result, as the evaluation score of the acupuncture treatment parameter of the historical knee osteoarthritis patient. The embodiment obtains the evaluation score of each acupuncture treatment parameter of each historical knee osteoarthritis patient by The addition result of the first important analysis value and the second important analysis value is negatively correlated and normalized, wherein exp is an exponential function with a natural constant as the base number. The addition result of the first important analysis value and the second important analysis value is negatively correlated and normalized, wherein exp is an exponential function with a natural constant as the base number.

[0082] At this point, the evaluation score of each acupuncture treatment parameter of each historical knee osteoarthritis patient is obtained, which is beneficial to the accurate training of the acupuncture efficacy prediction model in the subsequent.

[0083] The acupuncture efficacy prediction model acquisition module 40 is configured to train the acupuncture efficacy prediction model by using each acupuncture treatment parameter, evaluation score and acupuncture effect parameter of each historical knee osteoarthritis patient, and obtain a trained acupuncture efficacy prediction model.

[0084] Specifically, in order to train the acupuncture efficacy prediction model, the training proportion of the historical knee osteoarthritis patients is set to 7:3 in this embodiment, and the implementer can set the training proportion according to the actual situation, which is not limited here; and the loss function of the acupuncture efficacy prediction model is set as the mean square error. In the process of training the acupuncture efficacy prediction model, each acupuncture treatment parameter of each historical knee osteoarthritis patient and the evaluation score of each acupuncture treatment parameter are taken as the input of the acupuncture efficacy prediction model, and the acupuncture effect parameter of each historical knee osteoarthritis patient is taken as the output of the acupuncture efficacy prediction model, the acupuncture efficacy prediction model is trained, and the trained acupuncture efficacy prediction model is obtained.

[0085] For the current knee osteoarthritis patient who needs acupuncture treatment, the acupuncture treatment scheme of the knee osteoarthritis patient is set, and then the various acupuncture treatment parameters of the knee osteoarthritis patient can be obtained, and then the evaluation score of each acupuncture treatment parameter of the knee osteoarthritis patient is obtained. It should be noted that in the process of obtaining the evaluation score of each acupuncture treatment parameter of the knee osteoarthritis patient, when a certain acupuncture treatment parameter of the knee osteoarthritis patient exceeds the maximum range of the acupuncture treatment parameter, the local efficacy feedback value corresponding to the maximum acupuncture treatment parameter is taken as the local efficacy feedback value of the acupuncture treatment parameter of the knee osteoarthritis patient; when a certain acupuncture treatment parameter of the knee osteoarthritis patient is not within the range corresponding to the local efficacy feedback value of the acupuncture treatment parameter, but between the ranges corresponding to the adjacent two local efficacy feedback values, the local efficacy feedback value corresponding to the acupuncture treatment parameter of the knee osteoarthritis patient is calculated by distance proportional interpolation, for example, taking the frequency of electro-acupuncture as an example, assuming that the frequency of electro-acupuncture of the knee osteoarthritis patient is 4.5 Hz, which is located between the adjacent two electro-acupuncture frequency ranges 2 Hz-4 Hz and 5 Hz-6 Hz, wherein the local efficacy feedback value corresponding to 2 Hz-4 Hz is 0.9, and the local efficacy feedback value corresponding to 5 Hz-6 Hz is 0.5, then the local efficacy feedback value of the frequency of electro-acupuncture of the knee osteoarthritis patient is .

[0086] The various acupuncture treatment parameters and evaluation scores of the knee osteoarthritis patient are taken as inputs of the trained acupuncture effect prediction model, and then the acupuncture effect parameters of the knee osteoarthritis patient are output by the acupuncture effect prediction model; when the acupuncture effect parameters of the knee osteoarthritis patient are less than a preset acupuncture effect threshold, the doctor needs to further optimize the various acupuncture treatment parameters of the knee osteoarthritis patient, until the predicted acupuncture effect parameters of the knee osteoarthritis patient are greater than or equal to the preset acupuncture effect threshold, and the acupuncture treatment scheme of the knee osteoarthritis patient is determined. In this embodiment, the preset acupuncture effect threshold is set to 0.7, and the implementer can set the size of the preset acupuncture effect threshold according to the actual situation, which is not limited herein. Based on the effect prediction of the acupuncture effect prediction model, the doctor can predict the effect of the acupuncture treatment scheme for the knee osteoarthritis patient before the acupuncture treatment, provide a basis for formulating a personalized acupuncture treatment scheme for the knee osteoarthritis patient, and help improve the pertinence and effectiveness of the acupuncture treatment, so as to achieve better acupuncture treatment effect and improve the satisfaction of the knee osteoarthritis patient.

[0087] To sum up, in the embodiment, the acupuncture treatment parameters and acupuncture effect parameters of the historical knee osteoarthritis patients are obtained; the historical knee osteoarthritis patients are divided into patient categories based on the acupuncture effect parameters, the contribution degree is obtained according to the distribution of each acupuncture treatment parameter in each patient category and the difference from the distribution in other patient categories, the local effect feedback value is obtained according to the contribution degree and the acupuncture effect parameter, and then the evaluation score is obtained; the acupuncture effect prediction model is trained by the acupuncture treatment parameters, the evaluation score and the acupuncture effect parameters, and the trained acupuncture effect prediction model is obtained. The application accurately determines the participation degree of each acupuncture treatment parameter of each historical knee osteoarthritis patient by dynamically obtaining the evaluation score, and effectively improves the accuracy of the training of the acupuncture effect prediction model.

[0088] Embodiment 2:

[0089] The application also provides an acupuncture effect prediction device for knee osteoarthritis based on deep learning. The device comprises a memory and a processor, wherein the memory stores executable program codes, and the processor is configured to call and execute the executable program codes to execute the acupuncture effect prediction system for knee osteoarthritis based on deep learning provided in the embodiments. The device can be a chip, a component or a module. The chip can comprise a processor and a memory connected thereto. When the processor calls and executes the instructions, the chip can execute the acupuncture effect prediction system for knee osteoarthritis based on deep learning provided in the above embodiments.

[0090] In addition, the embodiments of the application also protect a computer device, please refer to Figure 3The computer device comprises a memory 401, a processor 402, and a computer program 403 stored in the memory 401 and running on the processor 402, wherein the processor 402 executes the computer program 403, so that the computer device can execute any one of the aforementioned deep learning-based knee osteoarthritis acupuncture efficacy prediction systems.

[0091] Embodiment 3

[0092] The application further provides a computer readable storage medium, which stores computer program codes, and when the computer program codes are run on a computer, the computer executes the above-mentioned related method steps to realize the deep learning-based knee osteoarthritis acupuncture efficacy prediction system provided in the above-mentioned embodiments.

[0093] Embodiment 4

[0094] The application further provides a computer program product, and when the computer program product is run on a computer, the computer executes the above-mentioned related steps to realize the deep learning-based knee osteoarthritis acupuncture efficacy prediction system provided in the above-mentioned embodiments.

[0095] Wherein, the device, the computer readable storage medium, the computer program product or the chip provided in the embodiment are used to execute the corresponding method provided above, so the beneficial effects that can be achieved are referable to the beneficial effects in the corresponding method provided above, which will not be repeated here.

[0096] It should be noted that: the above-mentioned sequence of the embodiments of the application is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0097] Each embodiment in the specification is described in a progressive manner, and the same and similar parts between each embodiment can be referred to each other, and each embodiment mainly describes the difference from other embodiments.

Claims

1. A deep learning-based acupuncture efficacy prediction system for knee osteoarthritis, characterized by: The system includes the following steps: A data acquisition module is used to obtain various acupuncture treatment parameters and acupuncture effect parameters of each historical knee osteoarthritis patient; A contribution degree acquisition module is used to divide historical knee osteoarthritis patients into patient categories based on acupuncture effect parameters, and obtain the contribution degree of each acupuncture treatment parameter in each patient category according to the distribution of each acupuncture treatment parameter in each patient category and the difference in distribution with other patient categories; the contribution degree is obtained by: obtaining the compactness of each acupuncture treatment parameter in each patient category according to the distribution of each acupuncture treatment parameter in each patient category; obtaining the specialness of each acupuncture treatment parameter in each patient category according to the difference in the compactness of each acupuncture treatment parameter in each patient category and other patient categories; and taking the product of the compactness and specialness of each acupuncture treatment parameter in each patient category as the contribution degree of each acupuncture treatment parameter in each patient category; An evaluation score acquisition module is used to obtain the efficacy contribution curve of each acupuncture treatment parameter based on the contribution degree and the acupuncture effect parameter in each patient category; obtain the local efficacy feedback value based on the changes in the efficacy contribution curve; and obtain the evaluation score of each acupuncture treatment parameter of each historical knee osteoarthritis patient based on each acupuncture treatment parameter and the corresponding local efficacy feedback value; an acupuncture efficacy prediction model acquisition module, configured to train an acupuncture efficacy prediction model using each acupuncture treatment parameter, evaluation score, and acupuncture effect parameter of each historical knee osteoarthritis patient to obtain a trained acupuncture efficacy prediction model; the acupuncture efficacy prediction model inputs are each acupuncture treatment parameter and the evaluation score of each acupuncture treatment parameter of each historical knee osteoarthritis patient, and the acupuncture efficacy prediction model outputs the acupuncture effect parameter of each historical knee osteoarthritis patient; The method for obtaining the degree of compactness is as follows: for any acupuncture treatment parameter and any patient category, the historical knee osteoarthritis patients in the patient category are clustered according to the size of the acupuncture treatment parameter of each historical knee osteoarthritis patient in the patient category using the DBSCAN density clustering algorithm, and the local category corresponding to the acupuncture treatment parameter in the patient category is obtained; the number of historical knee osteoarthritis patients in each local category is obtained and used as the number of local patients; the ratio of the maximum number of local patients to the number of all historical knee osteoarthritis patients in the patient category is used as the reference stability of the acupuncture treatment parameter in the patient category; the product of the reference stability and the inverse of the number of local categories is used as the compactness of the acupuncture treatment parameter in the patient category; The method for obtaining the degree of specialness is as follows: for any acupuncture treatment parameter and any patient category, obtain the mean value of the compactness of the acupuncture treatment parameter in all patient categories except the patient category as the first eigenvalue; use the difference between the compactness of the acupuncture treatment parameter in the patient category and the first eigenvalue as the first degree of distinction of the acupuncture treatment parameter in the patient category; obtain the mean value of the acupuncture treatment parameter of all patients with a history of knee osteoarthritis in the patient category as the overall reference value of the acupuncture treatment parameter in the patient category; obtain the mean value of the overall reference value of the acupuncture treatment parameter in all patient categories except the patient category as the second eigenvalue; use the difference between the overall reference value of the acupuncture treatment parameter in the patient category and the second eigenvalue as the second degree of distinction of the acupuncture treatment parameter in the patient category; and use the result of normalizing the sum of the first degree of distinction and the second degree of distinction as the degree of specialness of the acupuncture treatment parameter in the patient category.

2. The deep learning-based acupuncture efficacy prediction system for knee osteoarthritis according to claim 1, characterized in that: The method for obtaining the efficacy contribution curve is: The mean of the acupuncture effect parameters of all patients with historical knee OA in each patient category was used as the target effect parameter for each patient category; For any acupuncture treatment parameter, the contribution of the acupuncture treatment parameter in each patient category is taken as the y value in the two-dimensional coordinate, and the target effect parameter of each patient category is taken as the x value in the two-dimensional coordinate to obtain the reference coordinate of each patient category corresponding to the acupuncture treatment parameter; The points corresponding to the reference coordinates in the two-dimensional coordinate system are fitted into a curve as a contribution curve of the therapeutic effect of the acupuncture treatment parameters.

3. The deep learning-based acupuncture efficacy prediction system for knee osteoarthritis according to claim 1, characterized in that: The method for obtaining the local therapeutic effect feedback value is: For any efficacy contribution curve of acupuncture treatment parameters, the extreme value points on the efficacy contribution curve of the acupuncture treatment parameters are all used as segmentation points, and the efficacy contribution curve of the acupuncture treatment parameters is divided into multiple local curve segments; For any local curve segment, the ratio of the contribution range of the local curve segment to the overall contribution range of the efficacy contribution curve of the acupuncture treatment parameter is obtained as the local feedback degree of the local curve segment; The product of the slope of the local curve segment and the local feedback degree is used as a local efficacy feedback value of the acupuncture treatment parameter.

4. The deep learning-based acupuncture efficacy prediction system for knee osteoarthritis according to claim 3, characterized in that: The method for obtaining the evaluation score is: For any patient with a history of knee osteoarthritis and any acupuncture treatment parameter, the mean value of the acupuncture treatment parameter of all patients with a history of knee osteoarthritis in the patient category corresponding to the maximum local efficacy feedback value of the acupuncture treatment parameter is used as the target analysis value; The difference between the acupuncture treatment parameter of the patient with historical knee osteoarthritis and the target analysis value is used as the first important analysis value of the acupuncture treatment parameter of the patient with historical knee osteoarthritis; The difference between the local efficacy feedback value corresponding to the patient category of the acupuncture treatment parameter of the historical knee osteoarthritis patient and the maximum local efficacy feedback value of the acupuncture treatment parameter is used as the second important analysis value of the acupuncture treatment parameter of the historical knee osteoarthritis patient; The first important analysis value and the second important analysis value are added together, negatively correlated, and normalized to obtain the result, which is used as the evaluation score of the acupuncture treatment parameter for the patient with a history of knee osteoarthritis.

5. The deep learning-based acupuncture efficacy prediction system for knee osteoarthritis according to claim 1, characterized in that: The method for obtaining the patient category is: The DBSCAN density clustering algorithm was used to cluster the historical knee osteoarthritis patients according to the acupuncture effect parameters of each historical knee osteoarthritis patient to obtain the patient categories.

6. The deep learning-based acupuncture efficacy prediction system for knee osteoarthritis according to claim 1, characterized in that: The acupuncture effect parameter is a score given by doctors based on the treatment effect of each patient with a history of knee osteoarthritis after acupuncture treatment.

Images