Digital diagnosis and treatment intelligent analysis system for scoliosis diagnosis

Abstract

The invention relates to the technical field of digital diagnosis and treatment, and discloses a digital diagnosis and treatment intelligent analysis system for scoliosis diagnosis, which comprises a clinical data acquisition module, a scoliosis risk analysis module, a target data acquisition module, a scoliosis diagnosis module, a risk identification module and a man-machine interaction module, the scoliosis risk analysis module and the risk identification module are arranged, so that after the scoliosis category of the target object is obtained through the risk identification module, the disease risk of scoliosis is identified in combination with the Cobb angle value of the target object, and the risk of scoliosis is identified while the scoliosis diagnosis result of the target object is obtained. According to the scoliosis diagnosis method and system, the disease risk of scoliosis can be further obtained, scoliosis can be better controlled and prevented, proper intervention measures can be taken in time, further deterioration of scoliosis is prevented, the intelligence, rapidity and accuracy of scoliosis diagnosis are improved, and the severity of scoliosis is effectively prevented from being deepened.

Description

Technical Field

[0001] The present invention relates to the field of digital diagnosis and treatment technology, and more specifically to a digital diagnosis and treatment intelligent analysis system for scoliosis diagnosis. Background Art

[0002] Scoliosis is a common spinal deformity characterized by the bending of the spine to one side in the coronal plane, accompanied by rotation of the vertebral bodies and changes in kyphosis or lordosis in the sagittal plane. Scoliosis not only affects the patient's appearance, accelerates spinal degeneration and causes pain, but also leads to secondary chest deformity in severe cases, leading to cardiopulmonary dysfunction. Therefore, early detection and appropriate intervention measures are crucial to prevent the disease from worsening and help maintain the patient's health and living standards.

[0003] Traditional diagnosis of scoliosis mostly uses manual screening methods, such as flexion tests, scoliosis measuring tape, etc. However, traditional diagnostic methods have problems such as low efficiency, low degree of automation, and low accuracy. Therefore, an intelligent analysis system based on digital diagnosis is needed. Through three-dimensional laser scanning technology, scoliosis can be intelligently diagnosed. It has the characteristics of rapidity, high accuracy, and non-contact, so as to detect scoliosis early and take appropriate intervention measures to prevent the severity of scoliosis from worsening. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, the present invention provides a digital diagnosis and treatment intelligent analysis system for scoliosis diagnosis to solve the problems existing in the above-mentioned background technology.

[0005] The present invention provides the following technical solutions: a digital diagnosis and treatment intelligent analysis system for scoliosis diagnosis, comprising a clinical data acquisition module, a scoliosis risk analysis module, a target data acquisition module, a scoliosis diagnosis module, a risk identification module and a human-computer interaction module;

[0006] The clinical data acquisition module is used to collect clinical data of scoliosis patients and transmit it to the scoliosis risk analysis module;

[0007] The scoliosis risk analysis module is used to receive data from the clinical data acquisition module, perform cluster analysis to obtain scoliosis classification results, and then screen out factors closely related to the risk of scoliosis;

[0008] The target data acquisition module is used to acquire the spinal data of the target object and transmit it to the scoliosis diagnosis module and the risk identification module. The target data acquisition module includes a basic data entry unit and a scanning data acquisition unit;

[0009] The scoliosis diagnosis module is used to receive data from the scanning data acquisition unit, calculate the Cobb angle of the target object, perform scoliosis diagnosis based on the Cobb angle, and transmit the diagnosis results to the risk identification module and the human-computer interaction module;

[0010] The risk identification module is used to receive data from the scoliosis risk analysis module, the basic data entry unit and the scoliosis diagnosis module, analyze the scoliosis risk of the target object, and transmit it to the human-computer interaction module for display;

[0011] The human-computer interaction module is used to display the diagnosis result and the risk value of the target object.

[0012] Preferably, the spinal data includes basic data and scan data, the basic data entry unit is used to enter the target object's gender, age, disease type, severity, medical history characteristics and genetic characteristics, and transmit it to the risk identification module, the scan data acquisition unit is used to acquire the scan data of the target object, and transmit it to the scoliosis diagnosis module; the target object is an object that needs to be diagnosed with scoliosis; the basic data is the basic information of the target object, including gender, age, disease type, severity, medical history characteristics and genetic characteristics, and the scan data is a spinal scan image of the target object.

[0013] Preferably, the specific method of using the Cobb angle to diagnose scoliosis is:

[0014] When the Cobb angle is ≤10°, it is normal;

[0015] When 10°<Cobb angle≤25°, it is mild scoliosis;

[0016] When 25°<Cobb angle≤45°, it is moderate scoliosis;

[0017] When the Cobb angle is greater than 45°, it is severe scoliosis.

[0018] Preferably, the scoliosis risk analysis module obtains the scoliosis classification result in the following specific manner:

[0019] Step S11: construct a word vector conversion model to convert clinical data into corresponding word vectors;

[0020] Step S12: Take the converted n word vectors as sample points, randomly select k sample points as initial cluster centers, and mark them as z1, z2, z3, ..., z k ;

[0021] Step S13: record the sample points that are not used as cluster center points as calculation points and mark them as j1, j2, j3, ..., jn-k ; Calculate the distance D from each calculation point to each cluster center in turn ba , the calculation formula is expressed as: Among them, D ba is the bth calculation point j b To the a-th cluster center z a The distance, where b = 1, 2, 3, ..., nk; a = 1, 2, 3, ..., k; R is the dimension of the sample point, u = 1, 2, 3, ..., R; j bu is the bth calculation point j b The coordinates in the u-th dimension, z au is the a-th cluster center z a Coordinates in the u-th dimension;

[0022] Step S14: establishing corresponding k′ clusters based on the k cluster centers, k=k′;

[0023] Step S15: calculate point j b The distance to each cluster center is compared, and the calculated point is assigned to the cluster corresponding to the cluster center closest to it;

[0024] Step S16: set b=b+1, and jump back to step S15;

[0025] Step S17: Repeat steps S15 to S16 until b=nk, and the loop ends, and the nk calculation points are all assigned to the corresponding clusters;

[0026] Step S18: Recalculate the new cluster center coordinates of each cluster. The calculation formula is expressed as: Among them, z′ c is the new cluster center coordinate of the cth cluster, c = 1, 2, 3, ..., k', y i is the coordinate of the i-th calculation point in the c-th cluster, i = 1, 2, 3, ..., I, I is the total number of calculation points in the c-th cluster, y i =(y i1 ,y i2 ,y i3 ,...,y iR );

[0027] Step S19: Repeat steps S13 to S18 until the new cluster center coordinates of each cluster are recalculated in step S18, and the loop ends when the new cluster center coordinates of each cluster calculated in the previous loop are consistent; obtain the clusters and corresponding sample points corresponding to the k′ clusters;

[0028] The sample points corresponding to the k′ clusters are clinical data, and the scoliosis category corresponding to the clinical data of the new cluster center point of each cluster is selected as the scoliosis category of the cluster, that is, the cluster corresponding to the cluster.

[0029] Preferably, the screening of factors closely related to the risk of scoliosis comprises the following steps:

[0030] Step 1: Take the data in the clinical data as relevant factors, obtain N factors, encode them, obtain chromosomes, and construct the initial population;

[0031] Step 2: Determine the fitness function;

[0032] Step 3: natural selection of chromosomes in the population;

[0033] Step 4: Crossover recombination of chromosomes in the population;

[0034] Step 5: mutate the chromosomes in the population;

[0035] Step 6: Get a new population, preset the population generation number to be L, the fitness threshold to be Q, L is an integer greater than 0, and Q is a real number greater than 0; loop steps 3 to 5 until the generation number corresponding to the new population is L or the fitness corresponding to the chromosome in the new population is greater than or equal to the fitness threshold Q, the loop ends, and the factor corresponding to the chromosome with the maximum fitness in the new population is taken as the best factor, that is, the most closely related factor;

[0036] Step 7: Remove the best factor in step 6, repeat steps 3 to 5 to obtain a new best factor, until all factors have traversed the best factor, and then arrange them in positive order according to the order in which the best factors are obtained to obtain a factor sequence, and the clinical data item that is the first best factor is at the first place in the factor sequence;

[0037] Step 8: Obtain the factor sequences of k′ cluster centers in sequence; that is, obtain the factor arrangement related to different scoliosis categories.

[0038] Preferably, in step 2, the fitness function is expressed as: R =PP R , where F R is the fitness corresponding to the Rth chromosome, PP R is the matching degree of the factor corresponding to the Rth chromosome, R = 1, 2, 3, …, N.

[0039] Preferably, the method for obtaining the matching degree includes:

[0040] The clinical data corresponding to the scoliosis category and chromosome are used as analysis data, and the analysis data are input into the trained matching analysis model to predict the corresponding matching degree;

[0041] The specific training process of the matching degree analysis model includes:

[0042] Pre-collecting the matching degrees corresponding to a plurality of sets of analysis data, and converting the analysis data and the corresponding matching degrees into a corresponding set of feature vectors;

[0043] Each set of feature vectors is used as the input of the analysis model. The matching degree analysis model uses a set of predicted matching degrees corresponding to each set of analysis data as output, and uses the actual matching degree corresponding to each set of analysis data as the prediction target. The actual matching degree is the matching degree corresponding to the analysis data collected in advance. The training target is to minimize the sum of the prediction errors of all analysis data. The calculation formula of the prediction error is: Z K′ =(a K′ -μ K′ ) 2 , where Z K′ is the prediction error, K′ is the group number of the eigenvector corresponding to the analyzed data, a K′ is the predicted matching degree corresponding to the K′th group of analysis data, μ K′ is the actual matching degree corresponding to the K′th group of analysis data; the matching degree analysis model is trained until the sum of the prediction errors reaches convergence and the training is stopped;

[0044] The above matching degree analysis model is specifically a deep neural network model.

[0045] Preferably, the risk identification module analyzes the risk of scoliosis of the target object using the following formula:

[0046] Among them, δ is the risk of disease, γ is the number of selected factors closely related to the risk of scoliosis, β is the number of data items in the basic data items of the target object that are the same as the factors closely related to the risk of scoliosis, σ is the compensation coefficient, when the Cobb angle ≤10°, σ=1, when 10°<Cobb angle ≤25°, σ=2, when 25°<Cobb angle ≤45°, σ=3, when the Cobb angle>45°, σ=4.

[0047] Technical effects and advantages of the present invention:

[0048] The present invention is provided with a scoliosis risk analysis module and a risk identification module, which is conducive to obtaining scoliosis classification results through cluster analysis through clinical data, and screening out factors closely related to the risk of scoliosis. After obtaining the scoliosis category of the target object through the risk identification module, the risk of scoliosis is identified in combination with the Cobb angle value of the target object. Therefore, while obtaining the scoliosis diagnosis result of the target object, the risk of scoliosis can be further obtained, and scoliosis can be better controlled and prevented. Appropriate intervention measures can be taken in time to prevent further deterioration of scoliosis, improve the intelligence, rapidity and accuracy of scoliosis diagnosis, and effectively prevent the severity of scoliosis from worsening. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is a flow chart of the digital diagnosis and treatment intelligent analysis system for scoliosis diagnosis of the present invention. DETAILED DESCRIPTION

[0050] The technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention. In addition, the forms of the various structures recorded in the following embodiments are merely illustrative. The digital diagnosis and treatment intelligent analysis system for scoliosis diagnosis involved in the present invention is not limited to the various structures recorded in the following embodiments. All other implementations obtained by ordinary technicians in this field without making creative work belong to the scope of protection of the present invention.

[0051] The present invention provides a digital diagnosis and treatment intelligent analysis system for scoliosis diagnosis, including a clinical data acquisition module, a scoliosis risk analysis module, a target data acquisition module, a scoliosis diagnosis module, a risk identification module and a human-computer interaction module;

[0052] The clinical data collection module is used to collect clinical data of scoliosis patients, including but not limited to gender, age, disease type, severity, medical history characteristics, genetic characteristics, etc., and transmit it to the scoliosis risk analysis module;

[0053] The scoliosis risk analysis module is used to receive data from the clinical data acquisition module, perform cluster analysis to obtain scoliosis classification results, and then screen out factors closely related to the risk of scoliosis;

[0054] The target data acquisition module is used to acquire the spinal data of the target object and transmit it to the scoliosis diagnosis module and the risk identification module, the spinal data including basic data and scan data; the target data acquisition module includes a basic data entry unit and a scan data acquisition unit, the basic data entry unit is used to enter the gender, age, disease type, severity, medical history characteristics and genetic characteristics of the target object and transmit it to the risk identification module, the scan data acquisition unit is used to acquire the scan data of the target object and transmit it to the scoliosis diagnosis module; the target object is an object that needs to be diagnosed with scoliosis; the basic data is the basic information of the target object, including but not limited to gender, age, disease type, severity, medical history characteristics and genetic characteristics, etc., the scan data is a spinal scan image of the target object, which can be scanned using three-dimensional laser scanning technology or other scanning devices to acquire the scan image;

[0055] The scoliosis diagnosis module is used to receive data from the scanning data acquisition unit, calculate the Cobb angle of the target object, perform scoliosis diagnosis based on the Cobb angle, and transmit the diagnosis results to the risk identification module and the human-computer interaction module;

[0056] The risk identification module is used to receive data from the scoliosis risk analysis module, the basic data entry unit and the scoliosis diagnosis module, analyze the scoliosis risk of the target object, and transmit it to the human-computer interaction module for display;

[0057] The human-computer interaction module is used to display the diagnostic results and risk values ​​of the target object. When the risk value is too high, vigilance should be increased and the patient can be kept in the hospital for observation if necessary. Therefore, the diagnostic results and risk of scoliosis can be obtained at the same time.

[0058] In this embodiment, it should be specifically explained that the Cobb angle is a standard evaluation index for the spinal curvature angle, and the severity of scoliosis is divided into the following four levels:

[0059] When the Cobb angle is ≤10°, it is normal;

[0060] When 10°<Cobb angle≤25°, it is mild scoliosis;

[0061] When 25°<Cobb angle≤45°, it is moderate scoliosis;

[0062] When the Cobb angle is greater than 45°, it is severe scoliosis;

[0063] Therefore, the Cobb angle can be used to diagnose scoliosis and at the same time obtain the severity of scoliosis. The more severe the scoliosis, the higher the risk of scoliosis.

[0064] In this embodiment, it should be specifically explained that the specific method for the scoliosis risk analysis module to obtain the scoliosis classification result is:

[0065] Step S11: construct a word vector conversion model to convert clinical data into corresponding word vectors; the word vector conversion model is a BERT semantic model, which is a prior art method and will not be described in detail in this implementation;

[0066] Step S12: Take the converted n word vectors as sample points, randomly select k sample points as initial cluster centers, and mark them as z1, z2, z3, ..., z k ;

[0067] Step S13: record the sample points that are not used as cluster center points as calculation points and mark them as j1, j2, j3, ..., j n-k ; Calculate the distance D from each calculation point to each cluster center in turn ba , the calculation formula is expressed as: Among them, D ba is the bth calculation point j b To the a-th cluster center z a The distance, where b = 1, 2, 3, ..., nk; a = 1, 2, 3, ..., k; R is the dimension of the sample point, u = 1, 2, 3, ..., R; j bu is the bth calculation point j b The coordinates in the u-th dimension, z au is the a-th cluster center z a Coordinates in the u-th dimension;

[0068] Step S14: establishing corresponding k′ clusters based on the k cluster centers, k=k′;

[0069] Step S15: calculate point j b The distance to each cluster center is compared, and the calculated point is assigned to the cluster corresponding to the cluster center closest to it;

[0070] Step S16: set b=b+1, and jump back to step S15;

[0071] Step S17: Repeat steps S15 to S16 until b=nk, and the loop ends, and the nk calculation points are all assigned to the corresponding clusters;

[0072] Step S18: Recalculate the new cluster center coordinates of each cluster. The calculation formula is expressed as: Among them, z′ c is the new cluster center coordinate of the cth cluster, c = 1, 2, 3, ..., k', y iis the coordinate of the i-th calculation point in the c-th cluster, i = 1, 2, 3, ..., I, I is the total number of calculation points in the c-th cluster, y i =(y i1 ,y i2 ,y i3 ,...,y iR );

[0073] Step S19: Repeat steps S13 to S18 until the new cluster center coordinates of each cluster are recalculated in step S18, and the loop ends when the new cluster center coordinates of each cluster calculated in the previous loop are consistent; obtain the clusters and corresponding sample points corresponding to the k′ clusters;

[0074] The sample points corresponding to the k′ clusters are clinical data, and the scoliosis category corresponding to the clinical data of the new cluster center point of each cluster is selected as the scoliosis category of the cluster, that is, the cluster corresponding to the cluster.

[0075] In this embodiment, it should be specifically explained that the screening of factors closely related to the risk of scoliosis includes the following steps:

[0076] Step 1: Take the data in the clinical data as relevant factors, obtain N factors, encode them, obtain chromosomes, and construct the initial population;

[0077] Step 2: Determine the fitness function;

[0078] Step 3: natural selection of chromosomes in the population;

[0079] Step 4: Crossover recombination of chromosomes in the population;

[0080] Step 5: mutate the chromosomes in the population;

[0081] Step 6: Obtain a new population, preset the population generation number to be L, the fitness threshold to be Q, L is an integer greater than 0, and Q is a real number greater than 0; loop steps 3 to 5 until the generation number corresponding to the new population is L or the fitness corresponding to the chromosome in the new population is greater than or equal to the fitness threshold Q, the loop ends, and the factor corresponding to the chromosome with the maximum fitness in the new population is taken as the best factor, that is, the most closely related factor; illustratively, if the preset population generation number is 1, the chromosomes in the initial population are subjected to natural selection, crossover recombination and mutation to obtain a new population, and the generation number corresponding to the new population is 1 at this time, so the loop ends;

[0082] Step 7: Remove the best factor in step 6, repeat steps 3 to 5 to obtain a new best factor, until all factors have traversed the best factor, and then arrange them in positive order according to the order in which the best factors are obtained to obtain a factor sequence, and the clinical data item that is the first best factor is at the first place in the factor sequence;

[0083] Step 8: Obtain the factor sequences of k′ cluster centers in sequence; that is, the factors related to different scoliosis categories can be arranged, so that the factors closely related to the risk of scoliosis can be obtained. Those skilled in the art can select the top γ factors as closely related factors according to actual conditions;

[0084] In step 1, the N factors are encoded as U, where U is a chromosome, and N chromosomes are randomly generated to construct an initial population: C = {U1, U2, U3, ..., U N};

[0085] In step 2, the fitness function is expressed as: R =PP R , where F R is the fitness corresponding to the Rth chromosome, PP R is the matching degree of the factor corresponding to the Rth chromosome, R = 1, 2, 3, ..., N;

[0086] In the step 3, natural selection is performed by combining the elite method and the rotation method, wherein the elite method produces K1 offspring chromosomes, and for a population with a capacity of N, the fitness corresponding to the N chromosomes is arranged from large to small, and the K1 chromosomes at the front each produce a offspring chromosome, and the rotation method produces K2 offspring chromosomes, that is, N chromosomes produce K2 offspring chromosomes according to the corresponding rotation probability, wherein K1+K2=N;

[0087] The formula for the rotation probability is expressed as: Among them, P R is the rotation probability corresponding to the Rth chromosome;

[0088] In the step 4, G chromosomes are randomly selected from the population for crossover recombination to obtain G new chromosomes. The crossover recombination adopts the PMX method. After the chromosome crossover recombination, the fitness of the G new chromosomes is calculated, and the fitness of the G new chromosomes and the fitness of the G chromosomes are sorted from large to small, and a sorting table is generated. The G chromosomes in the sorting table are replaced with the G chromosomes in the population for crossover recombination in positive order;

[0089] In the step 5, the mutation probability is preset to T, and the N chromosomes in the population are mutated according to the mutation probability. The mutation method is to randomly select the positions of two genes in the chromosome and exchange the values ​​of the two genes.

[0090] In this embodiment, it should be specifically explained that the method for obtaining the matching degree includes:

[0091] The clinical data corresponding to the scoliosis category and chromosome are used as analysis data, and the analysis data are input into the trained matching analysis model to predict the corresponding matching degree;

[0092] The specific training process of the matching degree analysis model includes:

[0093] Pre-collecting the matching degrees corresponding to a plurality of sets of analysis data, and converting the analysis data and the corresponding matching degrees into a corresponding set of feature vectors;

[0094] Each set of feature vectors is used as the input of the analysis model. The matching degree analysis model uses a set of predicted matching degrees corresponding to each set of analysis data as output, and uses the actual matching degree corresponding to each set of analysis data as the prediction target. The actual matching degree is the matching degree corresponding to the analysis data collected in advance. The training target is to minimize the sum of the prediction errors of all analysis data. The calculation formula of the prediction error is: Z K′ =(a K′ -μ K′ ) 2 , where Z K′ is the prediction error, K′ is the group number of the eigenvector corresponding to the analyzed data, a K′ is the predicted matching degree corresponding to the K′th group of analysis data, μ K′ is the actual matching degree corresponding to the K′th group of analysis data; the matching degree analysis model is trained until the sum of the prediction errors reaches convergence and the training is stopped;

[0095] The above matching degree analysis model is specifically a deep neural network model.

[0096] In this embodiment, it should be specifically explained that the Cobb angle is calculated for scoliosis by determining the lower edge of the outer contour of the cone at the lower end of the spine and the upper edge of the outer contour of the cone at the upper end of the spine, and calculating the lower edge of the outer contour of the cone at the lower end of the spine and the upper edge of the outer contour of the cone at the upper end of the spine, and the angle between the lower edge of the outer contour of the cone at the lower end of the spine and the upper edge of the outer contour of the cone at the upper end of the spine is the Cobb angle.

[0097] In this embodiment, it should be specifically explained that the formula used by the risk identification module to analyze the risk of scoliosis of the target object is:

[0098] Among them, δ is the risk of disease, γ is the number of selected factors closely related to the risk of scoliosis, β is the number of data items in the basic data items of the target object that are the same as the factors closely related to the risk of scoliosis, σ is the compensation coefficient, when the Cobb angle ≤10°, σ=1, when 10°<Cobb angle ≤25°, σ=2, when 25°<Cobb angle ≤45°, σ=3, when the Cobb angle>45°, σ=4.

[0099] In the present embodiment, it should be specifically explained that the difference between the present embodiment and the prior art lies mainly in that the present embodiment is provided with a scoliosis risk analysis module and a risk identification module, which is conducive to obtaining scoliosis classification results through cluster analysis of clinical data, and screening out factors closely related to the risk of scoliosis. Thus, after obtaining the scoliosis category of the target object through the risk identification module, the risk of scoliosis is identified in combination with the Cobb angle value of the target object. Therefore, while obtaining the diagnostic result of scoliosis of the target object, the risk of scoliosis can be further obtained, scoliosis can be better controlled and prevented, and appropriate intervention measures can be taken in time to prevent further deterioration of scoliosis, improve the intelligence, rapidity and accuracy of scoliosis diagnosis, and effectively prevent the severity of scoliosis from worsening.

[0100] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0101] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A digital diagnosis and treatment intelligent analysis system for scoliosis diagnosis, characterized by: It includes clinical data acquisition module, scoliosis risk analysis module, target data acquisition module, scoliosis diagnosis module, risk identification module and human-computer interaction module; The clinical data acquisition module is used to collect clinical data of scoliosis patients and transmit it to the scoliosis risk analysis module; The scoliosis risk analysis module is used to receive data from the clinical data acquisition module, perform cluster analysis to obtain scoliosis classification results, and then screen out factors closely related to the risk of scoliosis; The target data acquisition module is used to acquire the spinal data of the target object and transmit it to the scoliosis diagnosis module and the risk identification module. The target data acquisition module includes a basic data entry unit and a scanning data acquisition unit; The scoliosis diagnosis module is used to receive data from the scanning data acquisition unit, calculate the Cobb angle of the target object, perform scoliosis diagnosis based on the Cobb angle, and transmit the diagnosis results to the risk identification module and the human-computer interaction module; The risk identification module is used to receive data from the scoliosis risk analysis module, the basic data entry unit and the scoliosis diagnosis module, analyze the scoliosis risk of the target object, and transmit it to the human-computer interaction module for display; The human-computer interaction module is used to display the diagnosis result and the risk value of the target object.

2. The digital diagnosis and treatment intelligent analysis system for scoliosis diagnosis according to claim 1, characterized in that: The spinal data includes basic data and scan data. The basic data entry unit is used to enter the target object's gender, age, disease type, severity, medical history characteristics and genetic characteristics, and transmit them to the risk identification module. The scan data acquisition unit is used to acquire the scan data of the target object and transmit it to the scoliosis diagnosis module. The target object is an object that needs to be diagnosed with scoliosis. The basic data is the basic information of the target object, including gender, age, disease type, severity, medical history characteristics and genetic characteristics, and the scan data is a spinal scan image of the target object.

3. The digital diagnosis and treatment intelligent analysis system for scoliosis diagnosis according to claim 1, characterized in that: The specific method of using the Cobb angle to diagnose scoliosis is: When the Cobb angle is ≤10°, it is normal; When 10°<Cobb angle≤25°, it is mild scoliosis; When 25°<Cobb angle≤45°, it is moderate scoliosis; When the Cobb angle is greater than 45°, it is severe scoliosis.

4. The digital diagnosis and treatment intelligent analysis system for scoliosis diagnosis according to claim 1, characterized in that: The specific method for the scoliosis risk analysis module to obtain the scoliosis classification result is: Step S11: construct a word vector conversion model to convert clinical data into corresponding word vectors; Step S12: Take the converted n word vectors as sample points, randomly select k sample points as initial cluster centers, and mark them as z1, z2, z3, ..., z k ; Step S13: record the sample points that are not used as cluster center points as calculation points and mark them as j1, j2, j3, ..., j n-k ; Calculate the distance D from each calculation point to each cluster center in turn ba , the calculation formula is expressed as: Among them, D ba is the bth calculation point j b To the a-th cluster center z a The distance, where b = 1, 2, 3, ..., nk; a = 1, 2, 3, ..., k; R is the dimension of the sample point, u = 1, 2, 3, ..., R; j bu is the bth calculation point j b The coordinates in the u-th dimension, z au is the ath cluster center z a Coordinates in the u-th dimension; Step S14: establishing corresponding k′ clusters based on the k cluster centers, k=k′; Step S15: calculate point j b The distance to each cluster center is compared, and the calculated point is assigned to the cluster corresponding to the cluster center closest to it; Step S16: set b=b+1, and jump back to step S15; Step S17: Repeat steps S15 to S16 until b=nk, and the loop ends, and the nk calculation points are all assigned to the corresponding clusters; Step S18: Recalculate the new cluster center coordinates of each cluster. The calculation formula is expressed as: Among them, z′ c is the new cluster center coordinate of the cth cluster, c = 1, 2, 3, ..., k', y i is the coordinate of the i-th calculation point in the c-th cluster, i = 1, 2, 3, ..., I, I is the total number of calculation points in the c-th cluster, y i =(y i1 ,y i2 ,y i3 ,...,y iR ); Step S19: Repeat steps S13 to S18 until the new cluster center coordinates of each cluster are recalculated in step S18, and the loop ends when the new cluster center coordinates of each cluster calculated in the previous loop are consistent; obtain the clusters and corresponding sample points corresponding to the k′ clusters; The sample points corresponding to the k′ clusters are clinical data, and the scoliosis category corresponding to the clinical data of the new cluster center point of each cluster is selected as the scoliosis category of the cluster, that is, the cluster corresponding to the cluster.

5. The digital diagnosis and treatment intelligent analysis system for scoliosis diagnosis according to claim 1, characterized in that: The screening of factors closely related to the risk of scoliosis includes the following steps: Step 1: Take the data in the clinical data as relevant factors, obtain N factors, encode them, obtain chromosomes, and construct the initial population; Step 2: Determine the fitness function; Step 3: natural selection of chromosomes in the population; Step 4: Crossover recombination of chromosomes in the population; Step 5: mutate the chromosomes in the population; Step 6: Get a new population, preset the population generation number to be L, the fitness threshold to be Q, L is an integer greater than 0, and Q is a real number greater than 0; loop steps 3 to 5 until the generation number corresponding to the new population is L or the fitness corresponding to the chromosome in the new population is greater than or equal to the fitness threshold Q, the loop ends, and the factor corresponding to the chromosome with the maximum fitness in the new population is taken as the best factor, that is, the most closely related factor; Step 7: Remove the best factor in step 6, repeat steps 3 to 5 to obtain a new best factor, until all factors have traversed the best factor, and then arrange them in positive order according to the order in which the best factors are obtained to obtain a factor sequence, and the clinical data item that is the first best factor is at the first place in the factor sequence; Step 8: Obtain the factor sequences of k′ cluster centers in sequence; that is, obtain the factor arrangement related to different scoliosis categories.

6. The digital diagnosis and treatment intelligent analysis system for scoliosis diagnosis according to claim 5, characterized in that: In step 2, the fitness function is expressed as: R =PP R , where F R is the fitness corresponding to the Rth chromosome, PP R is the matching degree of the factor corresponding to the Rth chromosome, R = 1, 2, 3, …, N.

7. A digital diagnosis and treatment intelligent analysis system for scoliosis diagnosis according to claim 6, characterized in that: The method for obtaining the matching degree includes: The clinical data corresponding to the scoliosis category and chromosome are used as analysis data, and the analysis data are input into the trained matching analysis model to predict the corresponding matching degree; The specific training process of the matching degree analysis model includes: Pre-collecting the matching degrees corresponding to a plurality of sets of analysis data, and converting the analysis data and the corresponding matching degrees into a corresponding set of feature vectors; Each set of feature vectors is used as the input of the analysis model. The matching degree analysis model uses a set of predicted matching degrees corresponding to each set of analysis data as output, and uses the actual matching degree corresponding to each set of analysis data as the prediction target. The actual matching degree is the matching degree corresponding to the analysis data collected in advance. The training target is to minimize the sum of the prediction errors of all analysis data. The calculation formula of the prediction error is: Z K′ =(a K′ -μ K′ ) 2 , where Z K′ is the prediction error, K′ is the group number of the eigenvector corresponding to the analyzed data, a K′ is the predicted matching degree corresponding to the K′th group of analysis data, μ K′ is the actual matching degree corresponding to the K′th group of analysis data; the matching degree analysis model is trained until the sum of the prediction errors reaches convergence and the training is stopped; The above matching degree analysis model is specifically a deep neural network model.

8. The digital diagnosis and treatment intelligent analysis system for scoliosis diagnosis according to claim 1, characterized in that: The formula used by the risk identification module to analyze the risk of scoliosis of the target object is: Among them, δ is the risk of disease, γ is the number of selected factors closely related to the risk of scoliosis, β is the number of data items in the basic data items of the target object that are the same as the factors closely related to the risk of scoliosis, σ is the compensation coefficient, when the Cobb angle ≤10°, σ=1, when 10°<Cobb angle ≤25°, σ=2, when 25°<Cobb angle ≤45°, σ=3, when the Cobb angle>45°, σ=4.

Images