Postoperative rehabilitation intervention system for patients with neurological diseases based on evidence-based medicine

Abstract

The present application relates to the technical field of postoperative rehabilitation, in particular to a postoperative rehabilitation intervention system for patients with neurological diseases based on evidence-based medical evidence. The steps implemented by the system include: obtaining characteristic data of a patient with a neurological disease to be analyzed and reference patients, a rehabilitation scheme of the reference patients and a postoperative Barthel index, calculating a reference factor of the reference patients corresponding to each rehabilitation scheme under each preoperative state; obtaining a comprehensive Barthel index of each rehabilitation scheme under each preoperative state by using the reference factor and the postoperative Barthel index, determining a correction factor under each preoperative state according to the comprehensive Barthel index, and correcting the comprehensive Barthel index to obtain a target Barthel index; determining a reference rehabilitation scheme by combining the similarity of the characteristic data of the patient with a neurological disease to be analyzed and different reference patients and the target Barthel index. The present application can improve the postoperative rehabilitation intervention effect for patients with neurological diseases.

Description

Technical Field

[0001] This invention relates to the field of postoperative rehabilitation technology, and more specifically to a postoperative rehabilitation intervention system for patients with neurological diseases based on evidence-based medicine. Background Technology

[0002] Brain tumors, as a type of neurological disease, usually compress surrounding brain tissue, blood vessels, and nerves, affecting the normal function of the nervous system. Surgical treatment is generally required to relieve the pressure of the brain tumor on the surrounding brain tissue and help patients recover various functions.

[0003] Existing KNN algorithms analyze rehabilitation programs for a large number of historical brain tumor patients to implement motor function rehabilitation interventions for the brain tumor patients to be analyzed. Specifically, a large number of historical brain tumor patients are collected. First, the motor function recovery under each preoperative condition and rehabilitation program is determined. Then, a KNN model is established using physiological state indicators. The data of the brain tumor patients to be analyzed are then substituted into the model to determine the postoperative rehabilitation intervention method for the current brain tumor patients. When determining the motor function recovery under each preoperative condition and rehabilitation program, because a large number of historical brain tumor patients are selected, there may be multiple historical brain tumor patients under a certain preoperative condition and rehabilitation program. Generally, the average Barthel Index of these patients is used to evaluate the motor function recovery under this preoperative condition and rehabilitation program. However, some patients may have special conditions such as other diseases, resulting in a large deviation between the postoperative Barthel Index and the normal index, which cannot reflect some general conditions and thus affect the postoperative rehabilitation intervention effect of the brain tumor patients to be analyzed. Summary of the Invention

[0004] To address the issue of poor intervention efficacy of existing methods in the postoperative rehabilitation of brain tumor patients, the present invention aims to provide an evidence-based rehabilitation intervention system for patients with neurological diseases. The specific technical solution adopted is as follows:

[0005] This invention provides a postoperative rehabilitation intervention system for patients with neurological diseases based on evidence-based medicine, comprising a memory and a processor, wherein the processor executes a computer program stored in the memory to achieve the following steps:

[0006] The study aims to acquire characteristic data from different dimensions of the patients with neurological diseases to be analyzed and several reference patients, as well as the rehabilitation plan and postoperative Barthel index of each reference patient. The reference patients are patients with neurological diseases.

[0007] Based on the discrete distribution characteristics of the postoperative Barthel index of all reference patients, the reference factor of each rehabilitation program for each reference patient in each preoperative state is obtained; using the proportion of the reference factor of each rehabilitation program for each reference patient in each preoperative state and the postoperative Barthel index, the comprehensive Barthel index of each rehabilitation program in each preoperative state is obtained, where the preoperative state is determined based on feature data.

[0008] The correction factor for each preoperative state is determined based on the comprehensive Barthel index; the comprehensive Barthel index is corrected using the correction factor to obtain the target Barthel index for each rehabilitation program under each preoperative state.

[0009] By combining the similarities between the characteristic data of the patients with neurological diseases to be analyzed and different reference patients, the proportion of reference patients corresponding to different rehabilitation programs, and the target Barthel index, a reference rehabilitation program for the patients with neurological diseases to be analyzed is determined.

[0010] Preferably, the step of obtaining the reference factors for each rehabilitation program corresponding to each preoperative state based on the discrete distribution characteristics of the Barthel index of all reference patients after surgery includes:

[0011] For the status to be evaluated:

[0012] For all reference patients in the evaluation state who adopted the candidate treatment after surgery, a two-dimensional rectangular coordinate system was drawn according to the magnitude of the postoperative Barthel index to obtain the data points corresponding to each reference patient in the evaluation state. The horizontal and vertical coordinates of the two-dimensional rectangular coordinate system are the postoperative Barthel index.

[0013] Obtain the local anomaly factor for each data point in the two-dimensional rectangular coordinate system;

[0014] The difference between constant 1 and the normalized value of the local abnormal factor of the data point corresponding to each reference patient in the state to be evaluated is used as the reference factor for each reference patient corresponding to the candidate scheme in the state to be evaluated.

[0015] The state to be evaluated is any preoperative state, and the candidate solution is any rehabilitation solution.

[0016] Preferably, the step of obtaining the comprehensive Barthel index for each rehabilitation program under each preoperative state by utilizing the proportion of reference factors for each reference patient corresponding to each rehabilitation program under each preoperative state and the postoperative Barthel index includes:

[0017] Calculate the first sum of reference factors for all reference patients corresponding to the candidate protocol under the state to be evaluated;

[0018] Calculate the first ratio between the reference factor of each reference patient corresponding to the candidate protocol under the state to be evaluated and the first sum value;

[0019] Based on the first ratio and the postoperative Barthel index of each reference patient corresponding to the candidate scheme under the evaluation state, the comprehensive Barthel index of the candidate scheme under the evaluation state is obtained. Both the first ratio and the postoperative Barthel index are positively correlated with the comprehensive Barthel index.

[0020] Preferably, based on the first ratio and the postoperative Barthel index of each reference patient corresponding to the candidate protocol under the evaluation state, the comprehensive Barthel index of the candidate protocol under the evaluation state is obtained, including:

[0021] The product of the first ratio and the corresponding postoperative Barthel index of the reference patient is used as the first characteristic value of the corresponding reference patient.

[0022] The sum of the first eigenvalues ​​of all reference patients corresponding to the candidate protocol under the evaluation state is determined as the comprehensive Barthel index of the candidate protocol under the evaluation state.

[0023] Preferably, determining the correction factor for each preoperative state based on the comprehensive Barthel index includes:

[0024] The maximum value of the combined Barthel Index of all rehabilitation programs under all preoperative conditions is recorded as the first maximum value;

[0025] The maximum value of the combined Barthel index of all rehabilitation programs under the evaluation state is recorded as the second maximum value;

[0026] The ratio between the first maximum value and the second maximum value is determined as the correction factor for the state to be evaluated.

[0027] Preferably, the step of using the correction factor to correct the comprehensive Barthel index to obtain the target Barthel index for each rehabilitation program under each preoperative condition includes:

[0028] The product of the correction factor under the evaluation state and the comprehensive Barthel index of the candidate scheme under the evaluation state is determined as the target Barthel index of the candidate scheme under the evaluation state.

[0029] Preferably, the step of determining the reference rehabilitation plan for the patient with the neurological disease to be analyzed by combining the similarity between the characteristic data of the patient to be analyzed and different reference patients, the proportion of reference patients corresponding to different rehabilitation plans, and the target Barthel index includes:

[0030] The PCA algorithm is used to reduce the dimensionality of the feature matrix to obtain the dimensionality-reduced data; the feature matrix is ​​composed of the feature data of all reference patients.

[0031] A KNN model is constructed based on the dimensionality-reduced data, and a first preset number of reference preoperative states are selected based on the KNN model.

[0032] All rehabilitation programs under the reference preoperative conditions are designated as the first reference programs; based on the target Barthel index of each first reference program under all reference preoperative conditions and the number of reference patients corresponding to each first reference program, the recommendation index of each first reference program is obtained.

[0033] Based on the recommendation indices of all first reference protocols, reference rehabilitation protocols for patients with neurological diseases to be analyzed were selected.

[0034] Preferably, the step of obtaining the recommendation index for each first reference protocol based on the target Barthel index for each first reference protocol under all reference preoperative conditions and the number of reference patients corresponding to each first reference protocol includes:

[0035] For any of the first reference schemes:

[0036] The ratio between the number of reference patients corresponding to the first reference protocol under each reference preoperative state and the total number of reference patients corresponding to the first reference protocol under all reference preoperative states is taken as the proportion of the number of patients under the first reference protocol under each reference preoperative state; the product of the proportion of the number of patients and the target Barthel index of the first reference protocol under each reference preoperative state is recorded as the second characteristic value of the first reference protocol under each reference preoperative state.

[0037] The recommendation index of the first reference scheme is obtained based on the overall distribution of the second feature value of the first reference scheme under all reference preoperative conditions.

[0038] Preferably, the step of screening reference rehabilitation programs for patients with neurological diseases to be analyzed based on the recommendation index of all first reference programs includes: sorting all first reference programs in descending order of recommendation index to obtain a rehabilitation program sequence, and determining the first preset second number of first reference programs in the rehabilitation program sequence as reference rehabilitation programs for patients with neurological diseases to be analyzed, wherein the preset second number is an integer greater than or equal to 1.

[0039] Preferably, the step of selecting a preset first number of reference preoperative states based on the KNN model includes:

[0040] The vector formed by the feature data of the patient with the neurological disease to be analyzed is multiplied by the feature matrix to obtain the position of the patient with the neurological disease to be analyzed in the KNN model; wherein the feature matrix is ​​formed by the feature vectors corresponding to the three principal components with the largest eigenvalues ​​during PCA dimensionality reduction.

[0041] Obtain the first set of preoperative states in the KNN model that are most similar to the patient with the neurological disease to be analyzed, and denote them as reference preoperative states.

[0042] The present invention has at least the following beneficial effects:

[0043] This invention first evaluates the reference value of each rehabilitation program for each preoperative state based on the discrete distribution characteristics of the Barthel Index of all reference patients, obtaining reference factors. Then, it combines the proportion of reference factors of each rehabilitation program for each preoperative state with the postoperative Barthel Index to obtain a comprehensive Barthel Index for each rehabilitation program for each preoperative state. The comprehensive Barthel Index better reflects the actual postoperative motor function recovery of patients. Based on the comprehensive Barthel Index, a correction factor is determined for each preoperative state, and the comprehensive Barthel Index is corrected to obtain a target Barthel Index. Finally, by combining the similarity between the characteristic data of the neurological disease patients to be analyzed and different reference patients, the proportion of reference patients corresponding to different rehabilitation programs, and the target Barthel Index, reference rehabilitation programs for the neurological disease patients to be analyzed are screened for doctors' reference, which can improve the postoperative rehabilitation intervention effect and accelerate the recovery speed of various functions after surgery. Attached Figure Description

[0044] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 This is a flowchart illustrating the method performed by a postoperative rehabilitation intervention system for patients with neurological diseases based on evidence-based medicine, as provided in an embodiment of the present invention. Detailed Implementation

[0046] To further illustrate the technical means and effects adopted by the present invention to achieve the intended purpose, the following detailed description, in conjunction with the accompanying drawings and preferred embodiments, describes a postoperative rehabilitation intervention system for patients with neurological diseases based on evidence-based medicine.

[0047] 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 this invention pertains.

[0048] The following description, in conjunction with the accompanying drawings, details a specific scheme for a postoperative rehabilitation intervention system for patients with neurological diseases based on evidence-based medicine, provided by this invention.

[0049] Example of a postoperative rehabilitation intervention system for patients with neurological diseases based on evidence-based medicine:

[0050] The specific scenario addressed in this embodiment is as follows: In order to reduce the postoperative rehabilitation time of patients with neurological diseases to be analyzed and enable the patients' various functions to recover to normal status quickly after surgery, rehabilitation intervention treatment is often carried out for postoperative patients. In the process of postoperative rehabilitation intervention for patients with neurological diseases to be analyzed, this embodiment combines the postoperative rehabilitation plans of patients in the past time period, the patient's indicators in different dimensions, and the postoperative recovery status to screen the rehabilitation plans of patients with similar conditions to the patients to be analyzed and provide them to doctors for reference.

[0051] This embodiment proposes a postoperative rehabilitation intervention system for patients with neurological diseases based on evidence-based medicine. This system aims to achieve, for example... Figure 1 The steps shown are as follows:

[0052] Step S1: Obtain characteristic data of different dimensions of the patient with the neurological disease to be analyzed and several reference patients, as well as the rehabilitation plan and postoperative Barthel index of each reference patient. The reference patients are patients with neurological diseases.

[0053] First, multi-dimensional feature data of multiple reference patients and patients with neurological diseases to be analyzed are collected from the database. In this embodiment, the feature data of each patient includes age, height, weight, number of disease types, tumor grade, and operation duration, i.e., multi-dimensional feature data of each patient is collected. In specific applications, the implementer can select the types of feature data according to the specific situation. Then, a rehabilitation plan for each reference patient is obtained. The rehabilitation plan includes drug group 1, drug group 2, drug group 3, etc., and physical therapy method 1, drug group 2, drug group 3, etc. It should be noted that the reference patients are all patients who have undergone brain tumor surgery and postoperative rehabilitation, and the patients with neurological diseases to be analyzed are patients who have undergone brain tumor surgery and need postoperative rehabilitation. In this embodiment, the number of reference patients is 200. In specific applications, the implementer can set it according to the specific situation. One month after the operation of each reference patient, the doctor assesses the motor function of each reference patient based on multiple items such as eating, dressing, bathing, toileting, gait, and movement transfer, and obtains the postoperative Barthel index of each reference patient. The process of obtaining the Barthel index is based on existing technology in Xi'an, and will not be elaborated further here.

[0054] Thus far, this embodiment has collected characteristic data of the patients with neurological diseases to be analyzed, characteristic data of each reference patient, rehabilitation plan of each reference patient, and postoperative Barthel index of each reference patient.

[0055] Step S2: Based on the discrete distribution characteristics of the postoperative Barthel index of all reference patients, obtain the reference factor for each rehabilitation program corresponding to each preoperative state; using the proportion of the reference factor of each rehabilitation program corresponding to each preoperative state and the postoperative Barthel index, obtain the comprehensive Barthel index of each rehabilitation program in each preoperative state, where the preoperative state is determined based on feature data.

[0056] In step S1 of this embodiment, data from multiple reference patients under different preoperative conditions and rehabilitation programs were collected. Each patient had a Barthel Index one month postoperatively. Because the rehabilitation of some extreme patients may be complex—for example, patients with multiple complications, older age, or weaker constitutions—the data may be significantly biased, and their postoperative Barthel Index may deviate considerably from the normal value, failing to reflect the general situation. Given that intervention programs typically rely on highly universal results, it is necessary to first determine the reference factors for each reference patient under each preoperative condition and each rehabilitation program to reflect the Barthel availability for each patient under different preoperative conditions and rehabilitation programs.

[0057] Since the number of patient instances selected for each preoperative condition and rehabilitation plan in this embodiment is sufficient, and a large sample size can improve the statistical significance of the results, most of these patients are normal patients. The Barthel index of relatively normal patients will show a clustering trend compared with the Barthel index of abnormal patients. Therefore, the more clustered the Barthel index, the higher its usability. So, we first calculate the reference factor for each reference patient through clustering, and then use the reference factor to weight the Barthel index of each patient under each preoperative condition and rehabilitation plan to obtain the comprehensive Barthel index for each preoperative condition and each rehabilitation plan in the example.

[0058] First, the preoperative status of each reference patient is determined based on all characteristic data collected. Two reference patients are considered to be in the same preoperative status if all characteristic data is identical; otherwise, they are not considered to be in the same preoperative status. In other words, the preoperative status of all reference patients is categorized into multiple types based on their characteristic data.

[0059] Next, this embodiment will analyze one rehabilitation plan and one preoperative condition as an example. Other rehabilitation plans and other preoperative conditions can be processed using the methods provided in this embodiment.

[0060] Specifically, any rehabilitation program is designated as a candidate program, and any preoperative state is designated as the state to be evaluated. For all reference patients in the state to be evaluated who adopted the candidate program postoperatively, a two-dimensional Cartesian coordinate system is plotted according to the magnitude of the postoperative Barthel index to obtain the data points corresponding to each reference patient in the state to be evaluated. The horizontal and vertical coordinates of the two-dimensional Cartesian coordinate system are both the postoperative Barthel index. The local abnormality factor of each data point in the two-dimensional Cartesian coordinate system is obtained. The method for obtaining the local abnormality factor of the data points is existing technology and will not be elaborated further here. The difference between the constant 1 and the normalized value of the local abnormality factor of the data point corresponding to each reference patient in the state to be evaluated is used as the reference factor for each reference patient corresponding to the candidate program in the state to be evaluated.

[0061] In this embodiment, a specific formula for calculating the reference factor is given. The reference factor for the i-th reference patient corresponding to the b-th rehabilitation plan under the a-th preoperative state can be expressed as:

[0062]

[0063] in, This represents the reference factor for the i-th reference patient corresponding to the b-th rehabilitation plan under the a-th preoperative state. Let represent the local abnormality factor of the data point corresponding to the i-th reference patient in the b-th rehabilitation plan under the a-th preoperative state, and norm() represents the normalization function.

[0064] The local anomaly factor is used to reflect the isolation of data points. The more dispersed the distribution of data points around the data point corresponding to the i-th reference patient, the larger the corresponding local anomaly factor. This is used to characterize the relative isolation of the data point corresponding to the i-th reference patient. The larger the local anomaly factor of the data point corresponding to the i-th reference patient, the more isolated the data point is, the smaller its clustering, i.e., the smaller the reference factor.

[0065] The higher the reference factor of the i-th reference patient corresponding to rehabilitation program b under preoperative condition a, the greater its contribution to the postoperative Barthel index of the patient under rehabilitation program b under preoperative condition a. Next, the postoperative Barthel index is weighted using the proportion of the reference factor of the reference patient corresponding to each rehabilitation program under each preoperative condition, to obtain the comprehensive Barthel index for each rehabilitation program under each preoperative condition.

[0066] Specifically, the first sum of reference factors for all reference patients corresponding to the candidate protocol under the evaluation state is calculated; the first ratio between the reference factor and the first sum of reference factors for each reference patient corresponding to the candidate protocol under the evaluation state is calculated; the product of the first ratio and the postoperative Barthel index of the corresponding reference patient is used as the first characteristic value of the corresponding reference patient after surgery; and the sum of the first characteristic values ​​of all reference patients corresponding to the candidate protocol under the evaluation state after surgery is determined as the comprehensive Barthel index of the candidate protocol under the evaluation state.

[0067] In this embodiment, a specific formula for calculating the comprehensive Barthel Index is given. The comprehensive Barthel Index of the rehabilitation program for the preoperative state a-th type can be expressed as:

[0068]

[0069] in, This represents the comprehensive Barthel Index of rehabilitation program b under preoperative condition a. This represents the number of reference patients corresponding to rehabilitation plan b under preoperative condition a. This represents the reference factor for the i-th reference patient corresponding to the b-th rehabilitation plan under the a-th preoperative state. This represents the postoperative Barthel index of the i-th reference patient corresponding to the b-th rehabilitation plan under the a-th preoperative state.

[0070] Indicates the first sum value. This represents the first ratio corresponding to the i-th reference patient in the b-th rehabilitation program under the a-th preoperative state. This represents the first characteristic value of the i-th reference patient corresponding to the b-th rehabilitation plan under the a-th preoperative state, reflecting the contribution of the i-th reference patient to the postoperative Barthel index under the b-th rehabilitation plan under the a-th preoperative state. The larger the first characteristic value and the larger the postoperative Barthel index of the reference patient corresponding to the b-th rehabilitation plan under the a-th preoperative state, the larger the overall Barthel index of the b-th rehabilitation plan under the a-th preoperative state.

[0071] Using the above method, the comprehensive Barthel index for each rehabilitation program under each preoperative condition can be obtained.

[0072] Step S3: Determine the correction factor for each preoperative state based on the comprehensive Barthel index; use the correction factor to correct the comprehensive Barthel index to obtain the target Barthel index for each rehabilitation program under each preoperative state.

[0073] The rehabilitation process is not only related to the rehabilitation program, but also to various preoperative conditions such as the patient's underlying health status and age. For example, young patients, even with a simple rehabilitation program, may recover very quickly due to their better physical condition, resulting in a more significant improvement in the Barthel Index. Older patients, while receiving the same rehabilitation measures, may recover more slowly due to physiological limitations, leading to a smaller increase in the Barthel Index. However, this does not necessarily mean that a rehabilitation program under a particular preoperative condition results in a poor recovery. It is necessary to adjust the overall Barthel Index of each rehabilitation program under each preoperative condition to ensure that patients with different preoperative conditions are assessed from the same starting point, reflecting the true extent of their recovery rather than simply biases caused by differences in preoperative conditions.

[0074] For each preoperative condition, the maximum Barthel Index obtained under all rehabilitation programs represents the maximum recovery capacity under that preoperative condition. To ensure that patients in different preoperative conditions start from the same point when assessing rehabilitation effects, their maximum recovery capacity can be used as a correction factor. If a patient's maximum recovery capacity is weak, even if their Barthel Index improves to some extent, they cannot be directly compared with patients in better preoperative health. Therefore, a relatively increased factor is needed to reflect their maximum effort and recovery potential in the current situation. Patients with strong maximum recovery capacity have relatively greater recovery potential. Therefore, their Barthel Index should be given a relatively decreased factor, as they are already at a relatively high recovery starting point and cannot achieve the same effect through the same degree of improvement.

[0075] Based on the above characteristics, the maximum value of the comprehensive Barthel Index of all rehabilitation programs under all preoperative conditions is recorded as the first maximum value; the maximum value of the comprehensive Barthel Index of all rehabilitation programs under the evaluation condition is recorded as the second maximum value; the ratio between the first maximum value and the second maximum value is determined as the correction factor under the evaluation condition. The product of the correction factor under the evaluation condition and the comprehensive Barthel Index of the candidate program under the evaluation condition is determined as the target Barthel Index of the candidate program under the evaluation condition.

[0076] Thus, by using the above method, the target Barthel index for each rehabilitation program under each preoperative condition can be obtained.

[0077] Step S4: By combining the similarity between the characteristic data of the patient with the neurological disease to be analyzed and different reference patients, the proportion of reference patients corresponding to different rehabilitation programs, and the target Barthel index, the reference rehabilitation program for the patient with the neurological disease to be analyzed is determined.

[0078] Since many factors influence the recovery of patients' motor function, and the scales of these factors are difficult to calculate and unify, and KNN performs poorly in high-dimensional spaces, this step uses Principal Component Analysis (PCA) to unify the feature scales of the preoperative state, reduce the dimensionality of the data, alleviate the curse of dimensionality, and make the established model more accurate.

[0079] Specifically, a feature matrix is ​​first constructed using the feature data of all reference patients. Each row of the feature matrix consists of feature data of all dimensions of a reference patient, and each column of the feature matrix consists of feature data of the same dimension of all reference patients. That is, one row represents one reference patient and one column represents one dimension.

[0080] The PCA algorithm is used to reduce the dimensionality of the feature matrix, obtain the eigenvectors corresponding to the three principal components with the largest eigenvalues, and obtain the dimensionality-reduced data; the PCA algorithm is an existing technology and will not be described in detail here.

[0081] The dimensionality-reduced data is plotted on a 3D image, thus constructing the KNN model. The three obtained feature vectors are used as the three columns of a matrix, meaning each element of a feature vector forms one column. This resulting matrix is ​​denoted as the feature matrix. Then, the vector formed by the feature data of the patient with the neurological disease to be analyzed is multiplied by the feature matrix to obtain a 3D vector. This 3D vector represents a point in the KNN model. Finding the point corresponding to this 3D vector within the KNN model represents the position of the patient with the neurological disease to be analyzed within the KNN model.

[0082] The preoperative states corresponding to a predetermined first number of data points in the KNN model that are most similar to the patient with the neurological disease to be analyzed are obtained and denoted as reference preoperative states. This means that the predetermined first number of nearest neighbor nodes corresponding to the patient with the neurological disease to be analyzed are obtained in the KNN model. The method for obtaining nearest neighbors is existing technology and will not be elaborated further here. All rehabilitation plans under the reference preoperative states are denoted as first reference plans, thus obtaining multiple first reference plans. In this embodiment, the predetermined first number is 10. In specific applications, the implementer can set this number according to specific circumstances.

[0083] For any rehabilitation program, patients in various preoperative states may have their data collected for that program. Each preoperative state has a corresponding comprehensive Barthel index for that rehabilitation program. Generally, the recommendability of a certain rehabilitation program is determined by the average Barthel index of that program across all reference preoperative states. However, to select a more universally applicable result, this embodiment will evaluate the recommendability of each first reference program based on the target Barthel index of each first reference program across all reference preoperative states and the number of reference patients corresponding to each first reference program, thereby obtaining a recommendation index for each first reference program.

[0084] For any of the first reference schemes:

[0085] The ratio between the number of reference patients corresponding to the first reference protocol under each reference preoperative state and the total number of reference patients corresponding to the first reference protocol under all reference preoperative states is taken as the proportion of the number of patients under the first reference protocol under each reference preoperative state; the product of the proportion of the number of patients and the target Barthel index of the first reference protocol under each reference preoperative state is recorded as the second characteristic value of the first reference protocol under each reference preoperative state; the recommendation index of the first reference protocol is obtained based on the overall distribution of the second characteristic value of the first reference protocol under all reference preoperative states.

[0086] In this embodiment, a specific formula for calculating the recommendation index is given. The recommendation index of the u-th first reference scheme can be expressed as:

[0087]

[0088] in, Let K represent the recommendation index of the u-th first reference plan, and K represent the number of reference preoperative states. This represents the number of reference patients corresponding to the u-th first reference protocol under the k-th reference preoperative state. Let represent the target Barthel index of the u-th first reference scheme under the k-th reference preoperative state.

[0089] This represents the percentage of patients with the u-th first reference regimen under the k-th reference preoperative state. It reflects the contribution rate of the u-th first reference regimen to the Barthel index of the k-th reference preoperative state. The larger this percentage is, the greater the contribution rate of the u-th first reference regimen to the Barthel index of the k-th reference preoperative state. The second characteristic value is denoted as . The higher the proportion of patients with the first reference protocol under each reference preoperative state and the higher the target Barthel index, the higher the recommendation index of the u-th first reference protocol.

[0090] Using the above method, a recommendation index for each first reference scheme can be obtained. A rehabilitation scheme with a higher recommendation index is more suitable for recommendation to the patient with the neurological disease to be analyzed. Therefore, all first reference schemes are sorted in descending order of recommendation index to obtain a rehabilitation scheme sequence. The first preset second number of first reference schemes in the rehabilitation scheme sequence are determined as reference rehabilitation schemes for the patient with the neurological disease to be analyzed, where the preset second number is an integer greater than or equal to 1. In this embodiment, the preset second number is 3, meaning the three first reference schemes with the highest recommendation index are used as reference rehabilitation schemes for the patient with the neurological disease to be analyzed. In specific applications, the implementer can set this according to specific circumstances.

[0091] When conducting rehabilitation interventions for patients with neurological disorders, doctors can refer to the reference rehabilitation plan for these patients to carry out corresponding rehabilitation treatments.

[0092] This embodiment first evaluates the reference value of each rehabilitation program for each preoperative state based on the discrete distribution characteristics of the Barthel Index of all reference patients, obtaining reference factors. Then, it combines the proportion of reference factors of each rehabilitation program for each preoperative state with the postoperative Barthel Index to obtain the comprehensive Barthel Index for each rehabilitation program for each preoperative state. The comprehensive Barthel Index better reflects the actual postoperative motor function recovery of patients. Based on the comprehensive Barthel Index, correction factors for each preoperative state are determined, and the comprehensive Barthel Index is corrected to obtain the target Barthel Index. Finally, by combining the similarity between the characteristic data of the neurological disease patients to be analyzed and different reference patients, the proportion of reference patients corresponding to different rehabilitation programs, and the target Barthel Index, reference rehabilitation programs for the neurological disease patients to be analyzed are screened for doctors' reference, which can improve the postoperative rehabilitation intervention effect and accelerate the recovery speed of various functions of patients after surgery.

[0093] In other embodiments, an apparatus is also provided, including a memory and a processor. The memory stores executable program code, and the processor calls and runs the executable program code from the memory, causing the apparatus to perform the methods described above in the evidence-based postoperative rehabilitation intervention system for patients with neurological diseases. Specifically, the apparatus may be a chip, component, or module. The chip may include a connected processor and memory; wherein the memory stores instructions, and when the processor calls and executes the instructions, the chip can perform the methods described above in the evidence-based postoperative rehabilitation intervention system for patients with neurological diseases.

[0094] In other embodiments, a computer program product is also provided, which, when run on a computer, causes the computer to perform the aforementioned related steps to implement the method performed by the evidence-based postoperative rehabilitation intervention system for patients with neurological diseases provided in the above embodiments.

[0095] In other embodiments, a computer-readable storage medium is also provided, which stores computer program code that, when executed on a computer, causes the computer to perform the aforementioned method steps to implement the method performed by the evidence-based postoperative rehabilitation intervention system for neurological disease patients provided in the above embodiments.

[0096] The systems, devices, computer program products, and computer-readable storage media provided are all used to execute the corresponding methods provided above. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0097] It should be noted that 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 principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A postoperative rehabilitation intervention system for patients with neurological diseases based on evidence-based medicine, comprising a memory and a processor, characterized in that, The processor executes a computer program stored in memory to perform the following steps: The study aims to acquire characteristic data from different dimensions of the patients with neurological diseases to be analyzed and several reference patients, as well as the rehabilitation plan and postoperative Barthel index of each reference patient. The reference patients are patients with neurological diseases. For all reference patients in the evaluation state who adopted the candidate treatment plan after surgery, a two-dimensional rectangular coordinate system was drawn according to the magnitude of the postoperative Barthel index to obtain the data points corresponding to each reference patient in the evaluation state. The horizontal and vertical coordinates of the two-dimensional rectangular coordinate system are the postoperative Barthel index. The local abnormal factor of each data point in the two-dimensional rectangular coordinate system was obtained. The difference between the constant 1 and the normalized value of the local abnormal factor of each reference patient in the evaluation state was used as the reference factor for each reference patient corresponding to the candidate treatment plan in the evaluation state. The evaluation state is any preoperative state, and the candidate treatment plan is any rehabilitation plan. The first sum of reference factors for all reference patients corresponding to the candidate protocol under the evaluation state is calculated. The first ratio between the reference factor and the first sum for each reference patient corresponding to the candidate protocol under the evaluation state is calculated. Based on the first ratio and the postoperative Barthel index of each reference patient corresponding to the candidate protocol under the evaluation state, the comprehensive Barthel index of the candidate protocol under the evaluation state is obtained. Both the first ratio and the postoperative Barthel index are positively correlated with the comprehensive Barthel index. The preoperative state is determined based on characteristic data. The maximum value of the combined Barthel index of all rehabilitation programs under all preoperative conditions is recorded as the first maximum value, and the maximum value of the combined Barthel index of all rehabilitation programs under the condition to be evaluated is recorded as the second maximum value. The ratio between the first maximum value and the second maximum value is determined as the correction factor under the condition to be evaluated. The overall Barthel index was corrected using a correction factor to obtain the target Barthel index for each rehabilitation program under each preoperative condition; By combining the similarities between the characteristic data of the patients with neurological diseases to be analyzed and different reference patients, the proportion of reference patients corresponding to different rehabilitation programs, and the target Barthel index, the reference rehabilitation program for the patients with neurological diseases to be analyzed is determined.

2. The postoperative rehabilitation intervention system for patients with neurological diseases based on evidence-based medicine according to claim 1, characterized in that, Based on the first ratio and the postoperative Barthel index of each reference patient corresponding to the candidate protocol in the evaluation state, the comprehensive Barthel index of the candidate protocol in the evaluation state is obtained, including: The product of the first ratio and the corresponding postoperative Barthel index of the reference patient is used as the first characteristic value of the corresponding reference patient. The sum of the first eigenvalues ​​of all reference patients corresponding to the candidate protocol under the evaluation state is determined as the comprehensive Barthel index of the candidate protocol under the evaluation state.

3. The postoperative rehabilitation intervention system for patients with neurological diseases based on evidence-based medicine according to claim 1, characterized in that, The composite Barthel index was adjusted using a correction factor to obtain the target Barthel index for each rehabilitation program under each preoperative condition, including: The product of the correction factor under the evaluation state and the comprehensive Barthel index of the candidate scheme under the evaluation state is determined as the target Barthel index of the candidate scheme under the evaluation state.

4. The postoperative rehabilitation intervention system for patients with neurological diseases based on evidence-based medicine according to claim 1, characterized in that, By combining the similarities between the characteristic data of the patients with neurological diseases to be analyzed and different reference patients, the proportion of reference patients corresponding to different rehabilitation programs, and the target Barthel index, reference rehabilitation programs for the patients with neurological diseases to be analyzed are determined, including: The PCA algorithm was used to reduce the dimensionality of the feature matrix to obtain the dimensionality-reduced data; the feature matrix was composed of the feature data of all reference patients. A KNN model is constructed based on the dimensionality-reduced data, and a first set of reference preoperative states are selected based on the KNN model. All rehabilitation programs under the reference preoperative conditions are designated as the first reference programs; based on the target Barthel index of each first reference program under all reference preoperative conditions and the number of reference patients corresponding to each first reference program, the recommendation index of each first reference program is obtained. Based on the recommendation indices of all first-reference protocols, reference rehabilitation protocols for patients with neurological diseases to be analyzed were selected.

5. The postoperative rehabilitation intervention system for patients with neurological diseases based on evidence-based medicine according to claim 4, characterized in that, Based on the target Barthel Index for each first reference protocol under all reference preoperative conditions and the number of reference patients corresponding to each first reference protocol, a recommendation index for each first reference protocol is obtained, including: For any of the first reference schemes: The ratio between the number of reference patients corresponding to the first reference protocol under each reference preoperative state and the total number of reference patients corresponding to the first reference protocol under all reference preoperative states is taken as the proportion of the number of patients under the first reference protocol under each reference preoperative state; the product of the proportion of the number of patients and the target Barthel index of the first reference protocol under each reference preoperative state is recorded as the second characteristic value of the first reference protocol under each reference preoperative state. The recommendation index of the first reference scheme is obtained based on the overall distribution of the second feature value of the first reference scheme under all reference preoperative conditions.

6. The postoperative rehabilitation intervention system for patients with neurological diseases based on evidence-based medicine according to claim 4, characterized in that, Based on the recommendation index of all first reference schemes, reference rehabilitation schemes for patients with neurological diseases to be analyzed are screened, including: sorting all first reference schemes in descending order of recommendation index to obtain a rehabilitation scheme sequence, and determining the first preset second number of first reference schemes in the rehabilitation scheme sequence as reference rehabilitation schemes for patients with neurological diseases to be analyzed, wherein the preset second number is an integer greater than or equal to 1.

7. The postoperative rehabilitation intervention system for patients with neurological diseases based on evidence-based medicine according to claim 4, characterized in that, Based on the KNN model, a first set of reference preoperative states were selected, including: The vector formed by the feature data of the patient with the neurological disease to be analyzed is multiplied by the feature matrix to obtain the position of the patient in the KNN model; where the feature matrix is ​​formed by the feature vectors corresponding to the three principal components with the largest eigenvalues ​​during PCA dimensionality reduction. Obtain the first set of preoperative states in the KNN model that are most similar to the patient with the neurological disease to be analyzed, and denote them as reference preoperative states.

Images