Intelligent Management System for Stroke Rehabilitation Effects Based on Digital Platform

Abstract

This invention relates to the technical field of information-based healthcare systems, specifically to an intelligent management system for stroke rehabilitation effectiveness based on a digital platform. The system includes a database, a modeling module, a data interface module, a computational processing module, a query module, a rehabilitation management module, and a data output module. The system constructs a rehabilitation assessment model fitted with a normal distribution, integrates patient physiological and motor index data, calculates rehabilitation index scores and rehabilitation degree scores, and achieves individualized and quantifiable rehabilitation effect assessment. The rehabilitation management module determines rehabilitation bias by using unidirectional and multidirectional mean deviation, and outputs results categorized as overall good, biased rehabilitation, and poor rehabilitation, supporting real-time feedback and rehabilitation intervention suggestions. The method includes model construction, data fitting testing, abnormal data processing and distribution characteristic analysis, adapts to multiple rehabilitation assessment indicators, and realizes dynamic tracking and intelligent management of the entire stroke rehabilitation process.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of information-based healthcare systems, and in particular to a stroke rehabilitation effect intelligent management system based on a digital platform. BACKGROUND

[0002] Stroke is an acute cerebrovascular disease caused by brain tissue damage due to blood supply disorders in the brain, with characteristics of high incidence, high disability rate and high recurrence rate. In patients with stroke sequelae, there are often problems such as motor disorders, language disorders, cognitive disorders and decreased activities of daily living, which urgently need to improve their functional recovery and quality of life through scientific and systematic rehabilitation intervention means.

[0003] Current clinical rehabilitation assessment and management of stroke mainly rely on subjective judgment of rehabilitation physicians, paper records and periodic physical examination data. Although various functional assessment scales (such as Fugl-Meyer scale, Barthel index, modified Rankin score, etc.) have been widely used, their assessment frequency is limited, data recording is scattered, and manual statistics is time-consuming, making it difficult to achieve dynamic monitoring and precise analysis of the whole cycle and whole dimension of the patient's rehabilitation process. In addition, there is a lack of unified assessment standards and information sharing mechanisms among different rehabilitation institutions, resulting in the "information island" problem of rehabilitation data, which further affects the optimization of rehabilitation programs and the quantitative management of therapeutic effect.

[0004] In recent years, the rapid development of digital medical care and artificial intelligence technology has provided a new solution path for stroke rehabilitation. With the help of intelligent algorithms, the rehabilitation progress of patients is modeled and evaluated, the recovery bottleneck is identified, the intervention rhythm is optimized, and the allocation efficiency of rehabilitation resources is improved. However, most existing digital platforms still have problems such as low integration, unintelligent evaluation algorithms, and lagging data updates, making it difficult to meet the high requirements of real-time, accuracy and continuity in the process of stroke rehabilitation. Therefore, it is urgent to design a stroke rehabilitation effect intelligent management system based on a digital platform to improve the visualization, intelligence and individualization of the rehabilitation process, thereby providing more scientific, efficient and precise rehabilitation services for stroke patients. SUMMARY

[0005] In view of the technical problems existing in the prior art, the present application provides a stroke rehabilitation effect intelligent management system based on a digital platform, which comprises a database, a modeling module, a data interface module, a calculation processing module, a query module, a rehabilitation management module and a data output module.

[0006] The database is used to store rehabilitation data, health data reference indicators, patient data, parameter distribution functions and rehabilitation management data.

[0007] The modeling module is configured to establish a rehabilitation evaluation model based on physiological indexes or motion indexes and conforming to normal distribution based on rehabilitation data, fit the rehabilitation data as a normal distribution function as a rehabilitation distribution function;

[0008] The data interface module is configured to receive stroke patient data from an external device, receive rehabilitation index scores and rehabilitation degree scores from the calculation processing module, and store the stroke patient data, rehabilitation index scores and rehabilitation degree scores to a database;

[0009] The calculation processing module is configured to calculate rehabilitation index scores and overall rehabilitation degree scores based on patient data and the rehabilitation evaluation model, and specifically includes:

[0010] C1, calculating rehabilitation index scores; calculating a standard deviation of the rehabilitation distribution function according to the rehabilitation evaluation model, calculating bilateral distribution probabilities of physiological indexes or motion indexes of a patient, calculating a standard deviation interval corresponding to bilateral distribution probabilities of a preset distribution proportion interval, and calculating rehabilitation index scores;

[0011] C2, calculating overall rehabilitation degree scores; including:

[0012] C21, dividing the patient into rehabilitation groups based on rehabilitation degree scores;

[0013] C22, performing K-S test, fitting test and normal distribution test on rehabilitation degree scores of each rehabilitation group, and inputting the normal distribution function to obtain a rehabilitation distribution function;

[0014] C23, calculating overall rehabilitation distribution of all rehabilitation groups;

[0015] C24, calculating unilateral distribution probabilities of rehabilitation degree scores, and calculating a standard deviation corresponding to unilateral distribution probabilities of a preset distribution proportion interval of overall rehabilitation degree scores, and calculating overall rehabilitation degree scores;

[0016] The query module is configured to receive a query instruction from a terminal to retrieve any one or a combination of multiple items of rehabilitation data, patient data and the rehabilitation evaluation model in the database;

[0017] The rehabilitation management module is configured to evaluate and manage rehabilitation index scores and overall rehabilitation degree scores; the data output module is configured to output the rehabilitation evaluation model to an external device, output query results to a terminal, and output management results of the rehabilitation management module.

[0018] Further, the specific steps of the rehabilitation management module include:

[0019] D1, calculation of unidirectional mean deviation; for each patient, calculate the rehabilitation index score according to the physiological index or the motion index, average all the rehabilitation index scores, and for each rehabilitation index score, calculate the unidirectional mean deviation;

[0020] D2, calculation of multidirectional mean deviation; for each patient, average all the rehabilitation index scores to obtain a multidirectional mean score, and further calculate the multidirectional mean deviation;

[0021] D3, judgment of bias; based on the unidirectional mean deviation and the multidirectional mean deviation, the bias of rehabilitation is evaluated.

[0022] Further, the judgment of bias includes the following three forms:

[0023] E1, the unidirectional mean deviation and the multidirectional mean deviation are both non-zero numbers, and the variance of the unidirectional mean deviation is less than the multidirectional mean deviation, then the overall rehabilitation is good;

[0024] E2, the unidirectional mean deviation and the multidirectional mean deviation are both non-zero numbers, and the variance of the unidirectional mean deviation is greater than the multidirectional mean deviation, then the bias rehabilitation is determined;

[0025] E3, the multidirectional mean deviation is zero, and the unidirectional mean deviation is non-zero, then the rehabilitation effect is poor.

[0026] Further, the physiological index or the motion index includes at least one of electroencephalogram (EEG), electromyogram (EMG), heart rate variability (HRV) and walking gait.

[0027] The application also provides a stroke rehabilitation effect intelligent management method based on a digital platform, comprising the following steps:

[0028] S1, system initialization; a stroke rehabilitation effect intelligent management system based on a digital platform is constructed and initialized;

[0029] S2, access of external data; through a data interface module, physiological indexes and motion indexes of stroke patients and patient basic parameters from external devices are received;

[0030] S3, data storage; the physiological indexes and motion indexes of stroke patients and patient basic parameters are stored to a database;

[0031] S4, construction of a rehabilitation evaluation model; based on historical data, a rehabilitation evaluation model is established;

[0032] S5, calculation of physiological parameters and evaluation scores, the physiological parameters and evaluation scores are fed back to the data interface module and stored to the database;

[0033] S6, rehabilitation effect management; based on the physiological parameters and the scores of the assessment, the rehabilitation effect of the patient is evaluated and managed.

[0034] Further, in step S4, the step of constructing the rehabilitation assessment model comprises:

[0035] S41, determination of an evaluation index; determining a physiological index or a movement index used to evaluate the rehabilitation effect as an evaluation index;

[0036] S42, data retrieval; retrieving the relevant data of historical patients in the database, i.e. the data of stroke patients, the scores of the rehabilitation indexes in the rehabilitation assessment model that are the same as the evaluation index, to form a data set;

[0037] S43, data cleaning and data integration; eliminating invalid data in the data set, reserving a position before adding new data, and recording mark information to facilitate subsequent data integration. The mark information includes actual data and fitted data of the evaluation index, mean values of the actual data and the fitted data of the evaluation index, scores, and basic number theory property inspection;

[0038] S44, data visualization; making a distribution point graph for the numerical values of the patient data;

[0039] S45, data fitting and fitting inspection; performing normal distribution inspection on the data. If the data meet the normal distribution, i.e. pass the fitting inspection, then proceed to step S46. Otherwise, proceed to the following data processing for data that do not pass the fitting inspection;

[0040] S46, obtaining a normal distribution function as a rehabilitation distribution function to establish a rehabilitation assessment model.

[0041] Further, the step of data processing for data that do not pass the fitting inspection comprises:

[0042] S451, if the sample number of the sequence is less than a preset rejection value, the sequence is considered to be meaningless, and the sequence is automatically eliminated. The mark information of data integration is modified;

[0043] S452, if the sample number of the sequence is greater than the preset rejection value, a data warning is automatically generated;

[0044] S453, labeling data that cannot be normally fitted, i.e. retrieving the data that cannot be normally fitted, recording them in a specified position in the rehabilitation assessment model, and calculating the mean value and the score;

[0045] S454, feeding back the numerical values and the mean value and score information to the data interface module, prompting the relevant data information through the data output module, and waiting for external instructions;

[0046] S455、If receiving the external instruction from the data interface about confirming the rejection, the series of data that cannot be fitted normally will be automatically rejected, and the marked information of the data fusion will be modified;

[0047] S456、If receiving the external instruction from the data interface about confirming the modification, the exact modification data on the data interface will be waited for, the modification data will be written, and the next time of data fusion will be carried out, the modified value will be taken as the historical data of the position;

[0048] S457、The external instruction for this data is received only once and needs to contain the option about modification or rejection, if receiving other instructions, the execution is refused, and the prompt instruction error is automatically fed back.

[0049] Further, the specific steps of calculating the physiological parameters and the score of evaluation in step S5 include:

[0050] S51、The actual value of the physiological parameter and the motion parameter is subjected to normal distribution test, if passing the normal distribution test, step S52 is executed, if not passing, step S53 is executed;

[0051] S52、The mean and score of the actual value are calculated, and the variance of the actual value is calculated;

[0052] S53、If not passing the normal distribution value, the data warning is automatically generated, the actual value is fed back to the data interface module, and the external device outputting the value is prompted about the actual value via the data output module.

[0053] Further, in step S6, the specific steps of rehabilitation effect management include:

[0054] S61、The calculation of one-way mean deviation degree; including:

[0055] S611、For each patient, the rehabilitation index score is calculated according to any one of the physiological index and the motion index;

[0056] S612、The mean of all rehabilitation index scores is calculated, and the one-way mean deviation degree is calculated for each rehabilitation index score;

[0057] S62、The calculation of multi-way mean deviation degree; for each patient, the mean of all rehabilitation index scores is calculated to obtain the multi-way mean score, and the multi-way mean deviation degree is further calculated;

[0058] S63、The judgment of bias; based on the one-way mean deviation degree and the multi-way mean deviation degree, the bias of rehabilitation is evaluated.

[0059] Further, the judgment of bias includes the following three forms:

[0060] S631, the one-way mean deviation and the multi-way mean deviation are both non-zero numbers, and the variance of the one-way mean deviation is less than the multi-way mean deviation, and it is determined that the overall rehabilitation is good;

[0061] S632, the one-way mean deviation and the multi-way mean deviation are both non-zero numbers, and the variance of the one-way mean deviation is greater than the multi-way mean deviation, and it is determined that the rehabilitation is biased;

[0062] S633, the multi-way mean deviation is zero, and the one-way mean deviation is non-zero, and it is determined that the rehabilitation effect is poor.

[0063] Further, when the biased rehabilitation is determined, the evaluation information is fed back to the terminal device outputting the numerical value through the data output module, the evaluation information includes the physiological parameter and the biased ratio of the motion parameter in the whole, and a prompt about increasing the weak item training is given.

[0064] Beneficial effects

[0065] The present application has the following beneficial effects:

[0066] 1. Realize the structured storage and intelligent modeling of multi-source data: the present application stores the rehabilitation data, patient basic data, health index reference value, parameter distribution function and management data through the database module, provides complete data support for rehabilitation evaluation modeling and statistical analysis, and establishes the rehabilitation evaluation function based on normal distribution fitting through the modeling module, so that the rehabilitation index has calculability and statistical significance, and lays a mathematical foundation for subsequent scoring and risk analysis.

[0067] 2. Improve the scientificity and precision of rehabilitation evaluation: the system introduces standard deviation probability interval, double-sided distribution probability and K-S test through the calculation processing module, realizes the quantitative output of rehabilitation index score and overall rehabilitation degree score, can reflect the current rehabilitation state, supports the comparison of stage effect, and effectively overcomes the shortcomings of traditional subjective scoring and qualitative judgment.

[0068] 3. Support hierarchical classification of rehabilitation intervention management: the rehabilitation management module calculates the one-way mean deviation and the multi-way mean deviation, establishes the rehabilitation effect bias determination mechanism, distinguishes three kinds of rehabilitation states of "overall good rehabilitation", "biased rehabilitation" and "poor rehabilitation effect", which is helpful for doctors to accurately identify the intervention key; when the biased rehabilitation is identified, the system can automatically feed back the training suggestion, prompt to strengthen the weak item function training, and realize the individualization adjustment of rehabilitation path.

[0069] 4. Enhance the data exception handling capability and security of the system: for the data that does not pass the normal distribution fitting, the application designs a perfect exception handling process, including automatic rejection, data warning, external instruction confirmation and other operations, to ensure that the rehabilitation model only adopts data with statistical significance; at the same time, the suspicious data is marked and tracked, the transparency and controllability of data management are improved, and the reliability of the analysis result is ensured. BRIEF DESCRIPTION OF DRAWINGS

[0070] Figure 1 It is a system structure schematic diagram of the application;

[0071] Figure 2 It is a method flow schematic diagram of the application. DETAILED DESCRIPTION

[0072] In order to deepen the understanding of the application, the application will be further described in combination with the embodiments below, and the embodiments are only used to explain the application and do not constitute a limitation on the protection scope of the application.

[0073] Embodiment 1

[0074] According to Figure 1 The embodiment provides a stroke rehabilitation effect intelligent management system based on a digital platform, which comprises a database, a modeling module, a data interface module, a calculation processing module, a query module, a rehabilitation management module and a data output module.

[0075] The database is used for storing rehabilitation data, health data reference indexes, patient data, parameter distribution functions and rehabilitation management data.

[0076] The modeling module is used for establishing a rehabilitation evaluation model based on physiological indexes or motion indexes and meeting normal distribution based on the rehabilitation data, fitting the rehabilitation data into a normal distribution function as a rehabilitation distribution function.

[0077] The data interface module is used for receiving stroke patient data from external equipment, receiving rehabilitation index scores and rehabilitation degree scores from the calculation processing module, and storing the stroke patient data, rehabilitation index scores and rehabilitation degree scores into the database.

[0078] The calculation processing module is used for calculating rehabilitation index scores and overall rehabilitation degree scores based on patient data and rehabilitation evaluation models.

[0079] The query module is used for receiving query instructions from terminals to retrieve any one or a combination of multiple items of rehabilitation data, patient data and rehabilitation evaluation models in the database.

[0080] The rehabilitation management module is used to evaluate and manage rehabilitation indicator scores and overall rehabilitation scores; the data output module is used to output rehabilitation assessment models to external devices, or output query results to terminals, as well as output the management results of the rehabilitation management module.

[0081] Example 2

[0082] This embodiment further defines the features of Embodiment 1: The calculation processing module calculates rehabilitation index scores and overall recovery scores based on patient data and a rehabilitation assessment model; specifically, it includes:

[0083] C1. Calculate rehabilitation index scores; based on the rehabilitation assessment model, calculate the standard deviation of the rehabilitation distribution function, obtain the bilateral distribution probability for the patient's physiological or motor indicators, obtain the standard deviation interval corresponding to the contralateral distribution probability for the preset distribution ratio interval, and calculate the rehabilitation index scores.

[0084] C2. Calculate the overall recovery score; including:

[0085] C21. Based on the recovery score, patients are divided into recovery groups. ,in, Indicates the first One rehabilitation group, Indicates the first The first rehabilitation group One patient;

[0086] The rehabilitation group satisfy:

[0087]

[0088] in, Indicates the patient's recovery score. and These represent the minimum and maximum values ​​of the patient's recovery rate, respectively. Indicates the group cutoff value;

[0089] C22. For each rehabilitation group recovery score Perform the KS test, fit test, and normality test, and substitute the normal distribution function to obtain the recovery distribution function;

[0090] C23. Calculate the overall rehabilitation distribution for all rehabilitation groups, satisfying:

[0091]

[0092] in, Represents the overall recovery distribution function; Indicates the first The rehabilitation distribution function of each rehabilitation group; Indicates the weight number;

[0093] C24. Calculate the one-sided distribution probability of the recovery score and the standard deviation of the one-sided distribution probability of the preset distribution ratio interval of the overall recovery score, and then calculate the overall recovery score.

[0094] Example 3

[0095] This embodiment further defines the features of Embodiment 1: the specific steps of the rehabilitation management module include:

[0096] D1. Calculation of one-way mean deviation: For each patient, calculate the rehabilitation index score based on physiological or motor indicators, average all rehabilitation index scores, and calculate the one-way mean deviation for each rehabilitation index score.

[0097] D2. Calculation of the deviation of the multi-directional mean: For each patient, the average of all rehabilitation index scores is calculated to obtain the multi-directional mean score, and then the deviation of the multi-directional mean is calculated.

[0098] D3. Determine bias; assess the bias of rehabilitation based on one-way mean deviation and multi-way mean deviation.

[0099] In step D1, the unidirectional mean deviation satisfies:

[0100]

[0101] in, Indicates that for the first One-way mean deviation of individual rehabilitation indicator scores; Indicates the first The actual value of each rehabilitation indicator score; Indicates the first The average score of each rehabilitation indicator;

[0102] The The formula for calculating the mean is:

[0103]

[0104] in, This represents the total score of the rehabilitation indicators.

[0105] In step D2, the unidirectional mean deviation satisfies:

[0106]

[0107] in, Indicates the degree of deviation from the mean in multiple directions; a multi-directional mean score representing all rehabilitation index scores.

[0108] The judgment of the bias includes the following three forms:

[0109] E1, the unidirectional mean deviation and the multi-directional mean deviation are both non-zero numbers, and the variance of the unidirectional mean deviation is less than the multi-directional mean deviation, then it is determined that the overall rehabilitation is good;

[0110] E2, the unidirectional mean deviation and the multi-directional mean deviation are both non-zero numbers, and the variance of the unidirectional mean deviation is greater than the multi-directional mean deviation, then it is determined that the rehabilitation is biased;

[0111] E3, the multi-directional mean deviation is zero, and the unidirectional mean deviation is non-zero, then it is determined that the rehabilitation effect is poor.

[0112] The physiological index or the motion index includes at least one of electroencephalogram (EEG), electromyogram (EMG), heart rate variability (HRV) and walking gait.

[0113] Embodiment 4

[0114] As shown in the figure: the embodiment is a stroke rehabilitation effect intelligent management method based on a digital platform, which includes the following steps: Figure 2

[0115] S1, system initialization; constructing and initializing a stroke rehabilitation effect intelligent management system based on a digital platform;

[0116] S2, access of external data; through a data interface module, receiving physiological indexes and motion indexes of stroke patients from external devices, and patient basic parameters;

[0117] S3, data storage; storing the physiological indexes and motion indexes of the stroke patients, and the patient basic parameters to a database;

[0118] S4, construction of a rehabilitation evaluation model; based on historical data, establishing a rehabilitation evaluation model;

[0119] S5, calculating physiological parameters and evaluation scores, feeding back the physiological parameters and evaluation scores to the data interface module, and storing them to the database;

[0120] S6, rehabilitation effect management; based on the physiological parameters and evaluation scores, evaluating and managing the rehabilitation effect of the patients.

[0121] Embodiment 5

[0122] The embodiment is further limited based on embodiment 4: in step S4, the step of constructing the rehabilitation evaluation model includes: ​

[0123] S41, determination of evaluation index; determine the physiological index or movement index used to evaluate the rehabilitation effect as the evaluation index;

[0124] S42, data retrieval; retrieve the relevant data of historical patients in the database, that is, the data of stroke patients and the scores of rehabilitation indicators in the rehabilitation evaluation model that are the same as the evaluation index, to form a data set;

[0125] S43, data cleaning and data integration; remove invalid data in the data set, reserve a position before adding new data, and record mark information to facilitate subsequent data integration. The mark information includes actual data and fitted data of the evaluation index, mean value of the actual data and the fitted data of the evaluation index, score and basic number theory property test;

[0126] S44, data visualization; make a distribution point graph for the numerical value of the patient data;

[0127] S45, data fitting and fitting test; make a normal distribution test of the data, and if it meets the normal distribution, it passes the fitting test and enters step S46, otherwise the following data processing of not passing the fitting test is performed;

[0128] S46, obtain a normal distribution function as a rehabilitation distribution function to establish a rehabilitation evaluation model.

[0129] The steps of data processing of not passing the fitting test include:

[0130] S451, if the sample number of the sequence is less than the preset rejection value, the sequence is considered meaningless and is automatically removed; and the mark information of data integration is modified;

[0131] S452, if the sample number of the sequence is greater than the preset rejection value, a data warning is automatically generated;

[0132] S453, mark the data that cannot be normally fitted, that is, retrieve the data that cannot be normally fitted, record it in a specified position in the rehabilitation evaluation model, and calculate the mean value and score;

[0133] S454, feed the numerical value itself and the mean value and score information back to the data interface module, prompt the relevant data information through the data output module, and wait for external instructions;

[0134] S455, if an external instruction about confirmation of removal is received from the data interface, the sequence that cannot be normally fitted is automatically removed, and the mark information of data integration is modified;

[0135] S456, if receiving the external instruction from the data interface about confirming the modification, waiting for the exact modification data on the data interface, writing the modification data, and next time when the data integration is performed, taking the modification data as the historical data of the position;

[0136] S457, the external instruction for this data is received only once and needs to contain the option about modification or elimination, if receiving other instructions, refusing to execute and automatically feeding back the prompt instruction error.

[0137] Embodiment 6

[0138] This embodiment is further limited based on embodiment 4: the specific steps of calculating the physiological parameters and the score of evaluation in step S5 include:

[0139] S51, normal distribution test is performed on the actual values of the physiological parameters and the motion parameters, if passing the normal distribution test, step S52 is executed; if not passing, step S53 is executed;

[0140] S52, the mean and the score of the actual values are calculated, and the variance of the actual values is calculated;

[0141] S53, if not passing the normal distribution value, automatically generating a data warning, feeding back the actual values to the data interface module, and prompting the external device outputting the values via the data output module to output the actual values.

[0142] Embodiment 7

[0143] This embodiment is further limited based on embodiment 4: in step S6, the specific steps of rehabilitation effect management include:

[0144] S61, calculation of one-way mean deviation; including:

[0145] S611, for each patient, calculating the rehabilitation index score according to any one of the physiological indicators and the motion indicators;

[0146] S612, calculating the one-way mean deviation for each rehabilitation index score by averaging all rehabilitation index scores;

[0147] S62, calculation of multi-way mean deviation; for each patient, averaging all rehabilitation index scores to obtain a multi-way mean score, and further calculating the multi-way mean deviation;

[0148] S63, judging the bias; based on the one-way mean deviation and the multi-way mean deviation, evaluating the bias of the rehabilitation.

[0149] In step S61, the one-way mean deviation satisfies:

[0150]

[0151] wherein, denotes the one-way mean deviation of the score of the i-th rehabilitation index; denotes the actual value of the score of the i-th rehabilitation index; denotes the mean value of the score of the i-th rehabilitation index;

[0152] The formula after averaging is:

[0153]

[0154] wherein, denotes the total amount of the scores of the rehabilitation indexes.

[0155] In step S62, the one-way mean deviation satisfies:

[0156]

[0157] wherein, denotes the multi-way mean deviation; denotes the multi-way mean score of all the rehabilitation indexes.

[0158] The judgment of the bias includes the following three forms: S631, both the one-way mean deviation and the multi-way mean deviation are non-zero numbers, and the variance of the one-way mean deviation is smaller than that of the multi-way mean deviation, then it is determined that the overall rehabilitation is good;

[0159] S632, both the one-way mean deviation and the multi-way mean deviation are non-zero numbers, and the variance of the one-way mean deviation is greater than that of the multi-way mean deviation, then it is determined that the rehabilitation is biased;

[0160] S633, the multi-way mean deviation is a zero number, and the one-way mean deviation is a non-zero number, then it is determined that the rehabilitation effect is poor.

[0161] When it is determined that the rehabilitation is biased, the evaluation information is fed back to the terminal device outputting the numerical value through a data output module, the evaluation information includes the bias ratio of the physiological parameters and the motion parameters in the whole, and a prompt about increasing the training of the weak items is given.

[0162] ​​​​The above shows and describes the basic principles, main features and advantages of the present application. Those skilled in the art should understand that the present application is not limited to the above-mentioned embodiments, and the above-mentioned embodiments and descriptions in the specification are only to illustrate the principles of the present application. Without departing from the spirit and scope of the present application, various changes and improvements can be made to the present application, and these changes and improvements all fall within the scope of the claimed present application. The scope of protection of the present application is defined by the appended claims and their equivalents.

Claims

1. A digital platform-based intelligent management system for stroke rehabilitation effects, characterized in that, The system comprises a database, a modeling module, a data interface module, a calculation processing module, a query module, a rehabilitation management module and a data output module. The database is used for storing rehabilitation data, health data reference indexes, patient data, parameter distribution functions and rehabilitation management data. The modeling module is used for establishing a rehabilitation evaluation model based on physiological indexes or movement indexes and conforming to normal distribution based on the rehabilitation data, fitting the rehabilitation data into a normal distribution function as a rehabilitation distribution function. The data interface module is used for receiving stroke patient data from external devices, receiving rehabilitation index scores and rehabilitation degree scores from the calculation processing module and storing the stroke patient data, rehabilitation index scores and rehabilitation degree scores into the database. The calculation processing module is used for calculating rehabilitation index scores and overall rehabilitation degree scores based on patient data and the rehabilitation evaluation model. The query module is used for receiving query instructions from terminals to retrieve any one or a combination of rehabilitation data, patient data and the rehabilitation evaluation model in the database. The rehabilitation management module is used for evaluating and managing rehabilitation index scores and overall rehabilitation degree scores. The rehabilitation management module comprises the following steps: D1, calculation of one-way mean deviation; for each patient, calculate rehabilitation index scores according to physiological indexes or movement indexes, calculate the mean value of all rehabilitation index scores and calculate one-way mean deviation for each rehabilitation index score; D2, calculation of multi-way mean deviation; for each patient, calculate the mean value of all rehabilitation index scores to obtain a multi-way mean score and further calculate multi-way mean deviation; D3, judgment of bias; evaluate the bias of rehabilitation based on one-way mean deviation and multi-way mean deviation. The judgment of bias comprises the following three forms: E1, both one-way mean deviation and multi-way mean deviation are nonzero numbers, and the variance of one-way mean deviation is smaller than that of multi-way mean deviation, indicating that the overall rehabilitation is good; E2, both one-way mean deviation and multi-way mean deviation are nonzero numbers, and the variance of one-way mean deviation is larger than that of multi-way mean deviation, indicating that the rehabilitation is biased; E3, multi-way mean deviation is zero, and one-way mean deviation is nonzero, indicating that the rehabilitation effect is poor. 2.The digital platform-based intelligent management system for stroke rehabilitation effects according to claim 1, characterized in that: The calculation processing module comprises the following steps: C1, calculation of rehabilitation index scores; calculate the standard deviation of the rehabilitation distribution function according to the rehabilitation evaluation model, calculate the bilateral distribution probability of the physiological indexes or movement indexes of the patient, calculate the standard deviation interval corresponding to the opposite distribution probability of the preset distribution proportion interval and calculate the rehabilitation index scores; C2, calculation of overall rehabilitation degree scores; comprising: C21, based on rehabilitation degree scores, divide the patient into rehabilitation groups; C22, K-S test, fitting test and normal distribution test are performed on the rehabilitation degree score of each rehabilitation group, and the normal distribution function is brought in to obtain the rehabilitation distribution function; C23, the overall rehabilitation distribution is calculated for all rehabilitation groups; C24, the one-sided distribution probability of the rehabilitation degree score is calculated, and the standard deviation corresponding to the one-sided distribution probability of the preset distribution proportion interval of the overall rehabilitation degree score is calculated to obtain the overall rehabilitation degree score. 3.The digital platform-based intelligent management system for stroke rehabilitation effects according to claim 1, characterized in that: The physiological indicators or motion indicators include at least one of electroencephalogram (EEG), electromyogram (EMG), heart rate variability (HRV) and walking gait.

4. An intelligent management method for stroke rehabilitation effect based on a digital platform, implemented based on the intelligent management system for stroke rehabilitation effect based on a digital platform according to any one of claims 1-3, comprising the following steps: S1, system initialization; constructing and initializing the intelligent management system for stroke rehabilitation effect based on a digital platform; S2, access of external data; receiving physiological indicators and motion indicators of stroke patients and patient basic parameters from external devices through a data interface module; S3, data storage; S4, construction of a rehabilitation evaluation model; based on historical data, a rehabilitation evaluation model is established; S5, calculation of physiological parameters and evaluation scores; the physiological parameters and evaluation scores are fed back to the data interface module and stored in the database; S6, rehabilitation effect management; based on the physiological parameters and evaluation scores, the rehabilitation effect of the patient is evaluated and managed. In step S4, the steps of constructing the rehabilitation evaluation model include: 5.The digital platform-based intelligent management method for stroke rehabilitation effect according to claim 4, characterized in that: S41, determination of evaluation indicators; determining physiological indicators or motion indicators used to evaluate the rehabilitation effect as evaluation indicators; S42, data retrieval; retrieving relevant data of historical patients in the database, i.e., stroke patient data and rehabilitation indicator scores in the rehabilitation evaluation model that are the same as the evaluation indicators, to form a data set; S43, data cleaning and data integration; invalid data in the data set is removed, a reserved position is reserved before new data is added, and label information is recorded for subsequent data integration; the label information includes actual data and fitted data of the evaluation indicators, mean values of the actual data and fitted data of the evaluation indicators, scores and basic number theory property tests; S44, data visualization; a distribution point graph is made for the numerical values of the patient data; S45, data fitting and fitting test; a normal distribution test is performed on the data, and if the normal distribution test is passed, the step S46 is entered, otherwise the following data processing for not passing the fitting test is performed; S46, obtaining a normal distribution function as a rehabilitation distribution function to establish a rehabilitation evaluation model. The specific steps of calculating the physiological parameters and evaluation scores in step S5 include: 6.The digital platform-based intelligent management method for stroke rehabilitation effect according to claim 5, characterized in that: S51, performing a normal distribution test on the actual values of the physiological parameters and motion parameters; if the normal distribution test is passed, step S52 is performed; if not, step S53 is performed; S52, calculating the mean value and score of the actual values, and calculating the variance of the actual values; ​ S53, if not passing normal distribution value, automatically generating data warning, feeding the actual value to the data interface module, and prompting the actual value to the external device outputting the value via the data output module. 7.The digital platform-based intelligent management method for stroke rehabilitation effect according to claim 6, characterized in that: In step S6, the specific steps of the rehabilitation effect management include: S61, calculation of one-way mean deviation; including: S611, for each patient, calculate the rehabilitation index score according to any one of the physiological indicators and the motion indicators; S612, average all rehabilitation index scores, and calculate the one-way mean deviation for each rehabilitation index score; S62, calculation of multi-way mean deviation; for each patient, average all rehabilitation index scores to obtain a multi-way mean score, and further calculate the multi-way mean deviation; S63, judging the bias; based on the one-way mean deviation and the multi-way mean deviation, evaluate the bias of the rehabilitation. 8.The digital platform-based intelligent management method for stroke rehabilitation effect according to claim 7, characterized in that: The judgment of the bias includes the following three forms: S631, both the one-way mean deviation and the multi-way mean deviation are non-zero, and the variance of the one-way mean deviation is less than that of the multi-way mean deviation, then the overall rehabilitation is good; S632, both the one-way mean deviation and the multi-way mean deviation are non-zero, and the variance of the one-way mean deviation is greater than that of the multi-way mean deviation, then the bias rehabilitation is determined; S633, the multi-way mean deviation is zero, and the one-way mean deviation is non-zero, then the rehabilitation effect is poor.

Images