CN114255873B - Exercise capacity assessment method and system for chronic kidney disease patient - Google Patents
Exercise capacity assessment method and system for chronic kidney disease patient Download PDFInfo
- Publication number
- CN114255873B CN114255873B CN202111579428.2A CN202111579428A CN114255873B CN 114255873 B CN114255873 B CN 114255873B CN 202111579428 A CN202111579428 A CN 202111579428A CN 114255873 B CN114255873 B CN 114255873B
- Authority
- CN
- China
- Prior art keywords
- exercise
- model
- user
- assessment
- test
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1118—Determining activity level
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/23—Updating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The invention discloses a method and a system for evaluating the exercise capacity of a patient with chronic kidney disease, wherein the method comprises the following steps: obtaining a first standard data set; acquiring first user health information, and constructing a first target movement capacity assessment model; performing a second exercise item test on the first user based on the exercise test index set to obtain a second standard data set; constructing a second target movement capacity assessment model; obtaining first model parameters and second model parameters; obtaining a third target movement capacity assessment model; and obtaining a movement capability assessment result. The method solves the technical problems that the motion ability assessment method of the chronic kidney disease patient is low in accuracy, the daily motion of the patient lacks specific scientific guidance, so that the motion effect is poor, and achieves the technical effects of accurately acquiring motion data of the chronic kidney disease patient, scientifically and reliably assessing the motion ability of the target chronic kidney disease patient, and improving the motion efficiency of the target patient.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a method and a system for evaluating the exercise capacity of a chronic kidney disease patient.
Background
The chronic nephrosis patient can not do intense exercise, the nephrosis is a chronic disease, people need to pay attention to a lot of rest and mainly take light physical activities, but the determination of the exercise scheme of the chronic nephrosis patient is often difficult, the reasonable exercise scheme and the reasonable exercise scheme optimizing method can play a role in well exercising the body and improving the individual physique and immunity, but excessive exercise or unreasonable exercise can lead to the morbidity of the chronic nephrosis patient, the chronic nephrosis patient has different influences due to the fact that the physique of the patient is different due to the fact that the chronic nephrosis patient takes hormone and immunosuppressant drugs for a long time, and the immune system damage condition possibly exists, so the exercise scheme of the chronic nephrosis patient can only be referred to by a doctor for diagnosis at present, the means for optimizing the exercise scheme is limited, and the exercise capability of the chronic nephrosis patient is reasonably assessed due to the difference of individual exercise capability.
In the prior art, the technical problems that the accuracy of the exercise capacity assessment method for chronic kidney disease patients is low, and the daily exercise of the patients lacks specific scientific guidance, so that the exercise effect is poor are solved.
Disclosure of Invention
According to the method and the system for evaluating the exercise capacity of the chronic kidney disease patient, the technical problems that the exercise effect is poor due to the fact that the accuracy of the exercise capacity evaluating method of the chronic kidney disease patient is low and the daily exercise of the patient lacks specific scientific guidance are solved, the exercise data of the chronic kidney disease patient are accurately acquired, the exercise capacity of the target chronic kidney disease patient is evaluated scientifically and reliably, and the exercise efficiency of the target patient is improved.
In view of the above, the present application provides a exercise ability assessment method and system for chronic kidney disease patients.
In a first aspect, the present application provides a method of assessing exercise capacity in a patient with chronic kidney disease, wherein the method comprises: performing a first exercise item test on a first user based on the exercise test index set to obtain a first standard data set; acquiring first user health information, training a long-term memory network model based on the first standard data set and the first user health information, and constructing a first target exercise capacity assessment model; performing a second exercise item test on the first user based on the exercise test index set to obtain a second standard data set; training the long-term and short-term memory network model based on the second standard data set and the first user health information, and constructing a second target movement capacity assessment model; extracting parameters of the first target movement capacity assessment model to obtain first model parameters, and extracting parameters of the second target movement capacity assessment model to obtain second model parameters; updating the long-term and short-term memory network model according to the first model parameter and the second model parameter to obtain a third target movement capacity evaluation model; and carrying out exercise capacity evaluation on the second user according to the third target exercise capacity evaluation model to obtain an exercise capacity evaluation result.
In another aspect, the present application provides a motor ability assessment system for a patient with chronic kidney disease, wherein the system comprises: the first obtaining unit is used for carrying out a first sports item test on a first user based on the sports test index set to obtain a first standard data set; the second obtaining unit is used for obtaining first user health information, training a long-term memory network model based on the first standard data set and the first user health information, and constructing a first target movement capacity assessment model; the third obtaining unit is used for carrying out a second exercise project test on the first user based on the exercise test index set to obtain a second standard data set; the first construction unit is used for training the long-period memory network model based on the second standard data set and the first user health information, and constructing a second target movement capacity assessment model; the fourth obtaining unit is used for extracting parameters of the first target movement capacity assessment model to obtain first model parameters, and extracting parameters of the second target movement capacity assessment model to obtain second model parameters; a fifth obtaining unit, configured to update the long-short-term memory network model according to the first model parameter and the second model parameter, to obtain a third target movement ability evaluation model; and the sixth obtaining unit is used for carrying out exercise capacity assessment on the second user according to the third target exercise capacity assessment model to obtain an exercise capacity assessment result.
In a third aspect, the present application provides a motor ability assessment system for a patient with chronic kidney disease, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method of any one of the first aspects when the program is executed.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
because the motion data of the chronic kidney disease patient is adopted, the long-term memory network model is combined, the health information of the chronic kidney disease patient is integrated with the motion data input model of the chronic kidney disease patient of a certain motion, the characteristic parameters are extracted, the motion data of the chronic kidney disease patient of different motion projects are different, different training models can be correspondingly obtained, the different models correspond to the different characteristic parameters, two or more sets of characteristic parameters are used for updating the model, the motion capability of the target chronic kidney disease patient is evaluated by combining the updated model with the information of the target chronic kidney disease patient, the technical problem that the motion capability evaluation method of the chronic kidney disease patient is not high in accuracy, the patient lacks specific scientific guidance in daily motion is solved, and therefore the poor motion effect is caused is achieved, the technical effect that the motion data of the chronic kidney disease patient is accurately acquired, the motion capability of the target chronic kidney disease patient is scientifically and reliably evaluated is achieved, and the motion efficiency of the target patient is improved is achieved.
The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
FIG. 1 is a flow chart of a method for assessing exercise capacity of a patient with chronic kidney disease according to the present application;
FIG. 2 is a schematic flow chart of a method for evaluating exercise ability of a patient with chronic kidney disease to obtain the first standard data set;
FIG. 3 is a schematic flow chart of a method for evaluating exercise ability of a patient with chronic kidney disease according to the present application;
FIG. 4 is a flow chart of a second user exercise effect assessment of the exercise ability assessment method of chronic kidney disease patients of the present application;
FIG. 5 is a schematic diagram of a motor ability assessment system for a patient with chronic kidney disease according to the present application;
fig. 6 is a schematic structural diagram of an exemplary electronic device of the present application.
Reference numerals illustrate: the device comprises a first obtaining unit 11, a second obtaining unit 12, a third obtaining unit 13, a first building unit 14, a fourth obtaining unit 15, a fifth obtaining unit 16, a sixth obtaining unit 17, an electronic device 300, a memory 301, a processor 302, a communication interface 303, and a bus architecture 304.
Detailed Description
According to the method and the system for evaluating the exercise capacity of the chronic kidney disease patient, the technical problems that the exercise effect is poor due to the fact that the accuracy of the exercise capacity evaluating method of the chronic kidney disease patient is low and the daily exercise of the patient lacks specific scientific guidance are solved, the exercise data of the chronic kidney disease patient are accurately acquired, the exercise capacity of the target chronic kidney disease patient is evaluated scientifically and reliably, and the exercise efficiency of the target patient is improved.
Summary of the application
The data acquisition, storage, use, processing and the like in the technical scheme meet the relevant regulations of national laws and regulations.
The chronic kidney disease patients need exercise to improve immunity, but individual variability exists in exercise ability of the chronic kidney disease patients, and the diagnosis and the explanation of doctors can only be used as references for determining exercise schemes, so that the establishment and optimization of reasonable exercise schemes of the chronic kidney disease patients have technical problems.
In the prior art, the technical problems that the accuracy of the exercise capacity assessment method for chronic kidney disease patients is low, and the daily exercise of the patients lacks specific scientific guidance, so that the exercise effect is poor are solved.
Aiming at the technical problems, the technical scheme provided by the application has the following overall thought:
the application provides a method for evaluating the exercise capacity of a patient with chronic kidney disease, wherein the method comprises the following steps: based on the motion data of the chronic kidney disease patient, the long-term memory network model is combined, the health information of the chronic kidney disease patient and the motion data input model of the chronic kidney disease patient of a certain motion are integrated, characteristic parameters are extracted, the motion data of the chronic kidney disease patient of different motion projects are different, different training models can be correspondingly obtained, the different models correspond to different characteristic parameters, two or more sets of characteristic parameters are used for updating the model, and the motion capability of the target chronic kidney disease patient is evaluated by using the updated model in combination with the information of the target chronic kidney disease patient.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
Example 1
As shown in fig. 1, the present application provides a method for evaluating exercise ability of a patient with chronic kidney disease, wherein the method comprises:
s100: performing a first exercise item test on a first user based on the exercise test index set to obtain a first standard data set;
Specifically, the exercise test index set includes a plurality of exercise test indexes including, but not limited to, exercise duration, exercise intensity or other relevant test indexes, and is specifically further refined according to the exercise project, and by way of simple illustration, the corresponding exercise index set corresponding indexes such as jogging include, but not limited to, running duration, running distance, running speed real-time data, and shall also include heart rate, blood pressure or other physical exercise data of the first user during exercise. The first user does not specifically refer to a certain user, and can be a plurality of patients suffering from chronic kidney disease, theoretically, the first user should comprise chronic kidney disease patients with different age stages and different sexes, the first exercise item can be fast walking, jogging, swimming, riding a bicycle, beating Tai Chi or other exercise suitable for the chronic kidney disease patients to perform moderate exercise, the first exercise item is determined, corresponding exercise indexes corresponding to the first exercise item can be determined, different exercise indexes correspond to different testing means, specific data acquisition can be specifically selected according to the exercise indexes, such as running time length can be measured and calculated by using a stopwatch, specific description is omitted, testing is completed, the exercise indexes are recorded, the records are collated to obtain a first standard data set, and a data basis is provided for data analysis.
S200: acquiring first user health information, training a long-term memory network model based on the first standard data set and the first user health information, and constructing a first target exercise capacity assessment model;
specifically, the first user health information includes, but is not limited to, user age, user gender, user weight information. The long-short-period memory network model is a neural network model in machine learning, is different from a conventional neural network model, can selectively store input data, ensures the reliability of training data of the model, takes the first standard data set and the first user health information as training data, inputs the long-short-period memory network model for training, can forget short-term abnormal data due to functional characteristics in the training process of the long-short-period memory network model, screens the input data of the model, takes repeated stable data as model training data, reduces the possibility that the accuracy of a first target movement capacity assessment model caused by the abnormal data participating in training is influenced, constructs the first target movement capacity assessment model, and provides a model foundation for the first target movement capacity assessment.
S300: performing a second exercise item test on the first user based on the exercise test index set to obtain a second standard data set;
specifically, the second exercise item is different from the first exercise item and suitable for chronic kidney disease patients, and can be fast walking, jogging, swimming, riding a bicycle, playing Taiji or other exercises suitable for chronic kidney disease patients to perform moderate exercises, a second exercise item test is determined, a test index and a test data acquisition mode are determined according to exercise item characteristics, and data are collated to obtain a second standard data set.
S400: training the long-term and short-term memory network model based on the second standard data set and the first user health information, and constructing a second target movement capacity assessment model;
specifically, the second standard data set and the first user health information are used as training data, the long-term and short-term memory network model is input, the training process is not repeated here, the second target exercise ability evaluation model is different from the first target exercise ability evaluation model, and the fact that the exercise ability evaluation is performed by directly using only jogging data is limited due to the fact that the jogging data is poor in jogging item exercise data index and good in playing Taiji exercise item exercise data index is illustrated by a simple example. In the examples, the explanation is for understanding the explanation of the steps of the scheme, in the examples, limitations are difficult to avoid due to objective factors, detailed analysis is not performed here, and practical application should be combined with actual data to perform specific analysis, which is not repeated here.
S500: extracting parameters of the first target movement capacity assessment model to obtain first model parameters, and extracting parameters of the second target movement capacity assessment model to obtain second model parameters;
specifically, the first target exercise capacity assessment model is different from the second target exercise capacity assessment model, different exercise capacity assessment on different aspects of the first user can be performed on different exercise capacity with exercise projects, parameters obtained by assessing the exercise capacity of the first user from different angles can fully embody the exercise capacity of the user as much as possible, locality of exercise capacity assessment data caused by single exercise project is reduced, and the exercise capacity assessment is performed only by playing Taiji projects by simple illustration, so that certain limitation of exercise capacity data can be avoided. And testing a plurality of sports projects and extracting parameters of the projects by using the long-short-period memory network model, so that the comprehensiveness of data in the process of carrying out the functional capacity assessment is ensured.
S600: updating the long-term and short-term memory network model according to the first model parameter and the second model parameter to obtain a third target movement capacity evaluation model;
Specifically, the first model parameter and the second model parameter are integrated to update the long-short-period memory network model differently from directly inputting the first standard data set, the second standard data set and the first user health information, the first standard data set and the first user health information are taken as a whole for different sports projects, the second standard data set and the first user health information are taken as another whole to respectively perform feature extraction, the first model parameter and the second model parameter are used to update the long-short-period memory network model to obtain a third target sports ability evaluation model, and the accuracy of a sports evaluation result of the updated third target sports ability evaluation model is higher, so that the rationality of input parameters is ensured.
S700: and carrying out exercise capacity evaluation on the second user according to the third target exercise capacity evaluation model to obtain an exercise capacity evaluation result.
Specifically, the second user is a chronic kidney disease patient needing exercise ability assessment, and may be a specific user with known user health information, where the specific user does not specifically fix a certain object, and needs to use the third target exercise ability assessment model to perform exercise ability assessment on the second user in combination with the health information of the second user needing exercise ability assessment, and the obtained result is an exercise ability assessment result of the second user. The reliability of the exercise capacity assessment model is guaranteed, and data reference is provided for the establishment of exercise schemes of chronic kidney disease patients.
Further, as shown in fig. 2, the step S100 further includes:
s110: constructing the exercise test index set, wherein the exercise test index set comprises heart rate, blood pressure, maximum oxygen uptake, blood sugar and subjective fatigue degree;
s120: performing the first exercise item test on the first user based on the exercise test index set, and acquiring time sequence data to obtain a first test data set;
s130: and carrying out data cleaning and normalization processing on the first test data set to obtain the first standard data set.
Specifically, the exercise test index set comprises a heart rate, a blood pressure, a maximum oxygen uptake, a blood sugar and a subjective fatigue degree, different index acquisition modes exist, the heart rate can be measured by using a portable heart rate measuring instrument, the blood pressure can be measured by using an electronic sphygmomanometer, the maximum oxygen uptake is expressed as the maximum oxygen uptake consumed in severe exercise, and the maximum oxygen uptake can be calculated by using a formula:
wherein->
Representing the maximum oxygen intake in milliliters (milliliters/kilogram/minute) of oxygen content per kilogram of body weight per minute, HRmax representing the maximum heart rate, and calculating by combining with the heart rate data can be carried in, and detailed calculation process is not repeated here; the subjective fatigue degree is mainly determined according to the feedback condition of the user, and the user can score the fatigue degree according to the muscle ache degree of the user as a reference; the first user is subjected to the first exercise item test based on the exercise test index set, time sequence data are collected, the time sequence data represent that each time point collects one data, then the collected data are fitted, and continuous data are obtained, namely a first test data set; and performing data cleaning and normalization processing on the first test data set, wherein the data cleaning is to remove abnormal data, for example, the blood sugar of a user is in a higher level due to diet, at the moment, the blood sugar measured by movement is easy to be abnormal, the data cleaning is required, the normalization processing is to change a dimensionless expression into a dimensionless expression to form a scalar, the normalization processing can effectively simplify calculation, and the data set obtained by conversion is the first standard data set. The data acquisition and the data preprocessing are completed, a data foundation is provided for the subsequent data analysis, and the subsequent data analysis is completed The operation data pretreatment is needed, and the operation can be effectively simplified.
Further, as shown in fig. 3, the obtaining the first user health information, training the long-term memory network model based on the first standard data set and the first user health information, and constructing a first target exercise ability assessment model, and step S200 further includes:
s210: obtaining the long-term and short-term memory network model;
s220: the first user health information is used as identification information, the first standard data set is identified, and the identified first standard data set is divided into a training set, a verification set and a test set;
s230: training the long-period memory network model based on the training set to obtain the weight and bias of the long-period memory network model, and generating a first exercise capacity assessment model;
s240: verifying the first movement capability assessment model based on the verification set to obtain a first verification result;
s250: if the first verification result is that the verification is passed, a second motion capability assessment model is obtained;
s260: if the first verification result is not passed, training the first movement capacity assessment model until the first verification result is passed, and obtaining the second movement capacity assessment model;
S270: and testing the second exercise capacity assessment model based on the test set to obtain the first target exercise capacity assessment model.
Specifically, the long-term and short-term memory network model is obtained, the long-term and short-term memory is a special neural network, the problems of gradient disappearance and gradient explosion can be solved in processing long sequences, and the long-term memory network model comprises four parts: forgetting gate, input gate, cell state update and output gate, the forgetting gate decides which information to discard from the cell state, the decision formula is f t ＝σ(W f ·[h t-1 ,x t ]+b f ) Wherein h is t-1 For the last transmission downStatus of coming, x t B, as input of the current node f For weight information, σ is a sigmoid activation function, the output is 0 to 1,0 indicates complete neglect, 1 indicates complete acceptance, the input gate is to determine which information is stored in the cell state, and the formula can be used: i.e t ＝σ(W i ·[h t-1 ，x t ]+b i ) Wherein b i The weight information is represented by a number of weight information,
wherein->
Representing a state that can be used to add to a cell, b c For weight information, the cell status update formula is +.>
Will be in cell state C t-1 Update to C t Old state C t-1 Multiplied by f t The cell state can be updated by forgetting the information to be forgotten, the output gate depends on the cell state, and the formula is used for expressing h t ＝o t *tanh(C t ) Wherein h is t Representing output o t ＝σ(W o [h t-1 ，x t ]+b o ) Wherein b o For weight information, sigma is a sigmoid activation function, and the long-and-short-term memory network model can greatly improve training efficiency in a long-sequence processing process; the first user health information is used as identification information, the first standard data set is identified, the identified first standard data set is divided into a training set, a verification set and a test set, and the data are divided, so that judgment on the long-period memory network model output is facilitated; training the long-period memory network model based on the training set to obtain the weight and bias of the long-period memory network model, generating a first exercise capacity assessment model, wherein in the exercise capacity judging process, the influence degree of different training data on a judging result is different, and the heart rate data can be simply interpreted from a certain rangeThe angle participates in the operation of the maximum respiration amount, so that the two should make corresponding trade-offs in the weight distribution process; verifying the first movement capability assessment model based on the verification set to obtain a first verification result; if the first verification result is that the verification is passed, a second motion capability assessment model is obtained; if the first verification result is not passed, training the first exercise capacity assessment model until the first verification result is passed, and obtaining the second exercise capacity assessment model, wherein the verification result shows that whether the output of the first exercise capacity assessment model meets the verification set is judged according to the first exercise capacity assessment model, and the judgment is irrelevant to the training times or other relevant factors; and testing the second movement capability assessment model based on the test set to obtain the first target movement capability assessment model, so that the reliability of the output of the first target movement capability assessment model is ensured, the characteristics of the first target movement capability assessment model are ensured to meet the preset requirements, and a basis is provided for the accuracy of model characteristic data.
Further, the step S700 further includes:
s710: constructing an expert system based on the expert domain knowledge base;
s720: transmitting the exercise capacity assessment result to the expert system, and carrying out grade assessment on the exercise capacity assessment result to obtain a first real-time grade;
s730: and obtaining first sports item information based on the first real-time level.
Specifically, an expert system is constructed based on a professional field knowledge base, the professional field knowledge base can be obtained by integrating information in big data after division, different sports projects can be divided into specific fields, and the sports fields can be divided into track and field, balls, swimming, bicycles or other sports projects by simple illustration, and the different sports fields have different sports characteristics; the exercise capacity assessment result is sent to the expert system, the exercise capacity assessment result is subjected to grade assessment, a first real-time grade is obtained, in short, if the user walks quickly, the user belongs to an athletic project, entry of the project is simpler, the user can be classified into basic exercise according to corresponding exercise grade classification, and the grade is lower; based on the first real-time level, first sports item information is obtained, wherein the first sports item information comprises sports items, intensity, frequency and time, the first real-time level participates in calculation in weight data calculation, detailed description is omitted in a specific process, different items are subjected to specific refinement judgment, a data basis is provided for subsequent data processing, meanwhile, rationality of the sports items is guaranteed, and a reasonable and reliable data source is provided for a sports ability evaluation system.
Further, as shown in fig. 4, the step S730 further includes:
s740: acquiring a first time period and a preset evaluation frequency based on the first sports item information;
s750: in the first time period, carrying out movement capacity assessment on the second user according to the preset assessment frequency to obtain a movement capacity assessment curve;
s760: in the first time period, carrying out health assessment on the second user to obtain a health assessment curve;
s770: performing curve fitting on the exercise capacity evaluation curve and the health evaluation curve to obtain a first fitted curve;
s780: and evaluating the movement effect of the second user based on the first fitting curve.
Specifically, based on the first exercise item information, a first time period and a preset evaluation frequency are obtained, wherein the first time period can be a week, every ten days, a month or other time period, and the preset evaluation frequency can be 3 times a week, 4 times a week or other exercise frequency data; in the first time period, performing exercise capacity assessment on the second user according to the preset assessment frequency to obtain an exercise capacity assessment curve, wherein in a normal condition, exercise capacity is relatively poor in an initial exercise stage, exercise is insisted, and exercise capacity is correspondingly improved; in the first time period, health evaluation is carried out on the second user to obtain a health evaluation curve, the exercise capacity can reflect the health condition of the second user in a certain condition, and research data show that people with good exercise habits are healthy and long-lived in general; performing curve fitting on the exercise capacity evaluation curve and the health evaluation curve to obtain a first fitted curve, wherein data are discontinuous data with sampling intervals, counting the data by using a chart, and fitting among data points to obtain the curve, namely the health evaluation curve; evaluating the motion effect of the second user based on the first fitting curve, and if the curve is close to the healthy condition, indicating that the motion effect of the second user is good; if the curve is relatively poor towards the health condition, the motion effect of the second user is relatively poor, the good and the poor are obtained by relatively comparing, the specific condition is not represented, and the actual analysis result is actually referred to for judgment.
Further, the present application further includes:
s810: collecting second user attribute information;
s820: performing feature analysis on the second user attribute information and the first fitting curve according to the expert system to obtain a first analysis result;
s830: obtaining a first adjustment instruction according to the first analysis result;
s840: and adjusting the first sports item information based on the first adjustment instruction.
In particular, second user attribute information is collected, including but not limited to user age, gender, weight, or other related body information data; according to the expert system, performing feature analysis on the second user attribute information and the first fitting curve to obtain a first analysis result, and simply illustrating that the second user is overweight, the track and field project is affected by the body weight, and particularly judging according to actual conditions; according to the first analysis result, a first adjustment instruction is obtained, and in combination with the fact that the first exercise item of the overweight second user is running in the above example, the first exercise item needs to be adjusted, and feature analysis can be performed on the attribute information of overweight of the second user and the first fitting curve through the expert system, so that a first analysis result is obtained, and further the first adjustment instruction is obtained; the first motion item information is adjusted based on the first adjustment instruction, and in combination with the above description in the example, the first motion may be adjusted to be a fast walking or a more suitable motion item in the same field, where the description in the example is for understanding a solution, and no specific solution analysis is performed, and the optimization should be specifically performed with reference to the actually obtained result. The method and the system ensure that the sports item meets the requirement of a second user, provide a data basis for further optimizing sports ability evaluation data, ensure the rationality of the first sports item of the second user and provide a basis for making a reasonable sports scheme for the second user.
Further, the present application further includes:
s850: obtaining a preset motion environment temperature threshold range;
s860: acquiring an actual movement environment temperature, and acquiring a second adjustment instruction if the actual movement environment temperature does not meet the preset movement environment temperature threshold range;
s870: and adjusting the first sports item information based on the second adjustment instruction.
Specifically, a preset exercise environment temperature threshold range is obtained, wherein the preset exercise environment temperature threshold range can be 18 ℃ to 25 ℃ or other environment temperature ranges suitable for exercise, particularly, chronic kidney disease patients possibly have immune system damage condition due to long-term administration of hormone and immunosuppressant drugs, and chronic kidney disease patients catch cold easily to cause chronic kidney disease, so that the suitable environment temperature is a basis for reasonable exercise; the actual movement environment temperature is obtained, the acquisition mode can be realized by adopting an alcohol thermometer, if the actual movement environment temperature does not meet the preset movement environment temperature threshold range, simply speaking, the temperature needs to be judged to be lower than the preset temperature or higher than the preset temperature, a specific gap is determined, and after the determination, the measurement can be carried out according to actual data, so that a second adjustment instruction is obtained; based on the second adjustment instruction, the first sports item information is adjusted, and the simple explanation is that the winter suitable sports item is different from the summer suitable sports item, and when the sports item is determined, the environment temperature is input to assist in optimizing the first sports item, so that the rationality and the practicability of the first sports item can be ensured.
In summary, the exercise capacity evaluation method and system for chronic kidney disease patients provided by the application have the following technical effects:
1. because the first exercise project test is carried out on the first user based on the exercise test index set, a first standard data set is obtained; acquiring first user health information, training a long-term memory network model based on the first standard data set and the first user health information, and constructing a first target exercise capacity assessment model; performing a second exercise item test on the first user based on the exercise test index set to obtain a second standard data set; training the long-term and short-term memory network model based on the second standard data set and the first user health information, and constructing a second target movement capacity assessment model; extracting parameters of the first target movement capacity assessment model to obtain first model parameters, and extracting parameters of the second target movement capacity assessment model to obtain second model parameters; updating the long-term and short-term memory network model according to the first model parameter and the second model parameter to obtain a third target movement capacity evaluation model; and carrying out exercise capacity evaluation on the second user according to the third target exercise capacity evaluation model to obtain an exercise capacity evaluation result. According to the method and the system for evaluating the exercise capacity of the chronic kidney disease patient, the technical problems that the exercise effect is poor due to the fact that the accuracy of the exercise capacity evaluating method of the chronic kidney disease patient is low and the daily exercise of the patient lacks specific scientific guidance are solved, the exercise data of the chronic kidney disease patient are accurately acquired, the exercise capacity of the target chronic kidney disease patient is evaluated scientifically and reliably, and the exercise efficiency of the target patient is improved.
2. Because the long-period memory network model is adopted, and the health information of the chronic kidney disease patient is used as the identification information verification model, the exercise capacity assessment model is obtained through verification, the reliability of the output of the first target exercise capacity assessment model is ensured, the feature of the first target exercise capacity assessment model is ensured to meet the preset requirement, and a foundation is provided for the accuracy of model feature data.
3. The expert system is adopted to analyze the sports item, so that the technical effects of providing professional sports item suggestions for users and scientifically evaluating sports conditions are achieved, different items are subjected to specific refinement judgment, a data basis is provided for subsequent data processing, the rationality of the sports item is ensured, and a reasonable and reliable data source is provided for the sports ability evaluation system.
4. Because the real-time collection of the movement environment temperature is adopted, the movement project is regulated timely according to the movement environment temperature, and the environment temperature is input when the movement project is determined, so that the first movement project is assisted to be optimized, and the rationality and the practicability of the first movement project can be ensured.
Example two
Based on the same inventive concept as the exercise capacity assessment method of a chronic kidney disease patient in the foregoing embodiments, as shown in fig. 5, the present application provides a system for exercise capacity assessment of a chronic kidney disease patient, wherein the system comprises:
A first obtaining unit 11, where the first obtaining unit 11 is configured to perform a first exercise item test on a first user based on an exercise test index set, to obtain a first standard data set;
a second obtaining unit 12, where the second obtaining unit 12 is configured to obtain first user health information, train a long-term memory network model based on the first standard data set and the first user health information, and build a first target exercise ability evaluation model;
a third obtaining unit 13, where the third obtaining unit 13 is configured to perform a second exercise item test on the first user based on the exercise test index set, to obtain a second standard data set;
a first construction unit 14, where the first construction unit 14 is configured to train the long-term and short-term memory network model based on the second standard data set and the first user health information, and construct a second target exercise ability assessment model;
a fourth obtaining unit 15, where the fourth obtaining unit 15 is configured to perform parameter extraction on the first target motion capability assessment model to obtain a first model parameter, and perform parameter extraction on the second target motion capability assessment model to obtain a second model parameter;
a fifth obtaining unit 16, where the fifth obtaining unit 16 is configured to update the long-short-term memory network model according to the first model parameter and the second model parameter, to obtain a third target exercise capability assessment model;
And a sixth obtaining unit 17, where the sixth obtaining unit 17 is configured to perform exercise capability assessment on the second user according to the third target exercise capability assessment model, to obtain an exercise capability assessment result.
Further, the system includes:
the second construction unit is used for constructing the exercise test index set, and the exercise test index set comprises heart rate, blood pressure, maximum oxygen uptake, blood sugar and subjective fatigue degree;
a seventh obtaining unit, configured to perform the first exercise item test on the first user based on the exercise test index set, collect time-series data, and obtain a first test data set;
and the eighth obtaining unit is used for carrying out data cleaning and normalization processing on the first test data set to obtain the first standard data set.
Further, the system includes:
a ninth obtaining unit, configured to obtain the long-short-period memory network model;
the first dividing unit is used for marking the first standard data set by taking the first user health information as marking information and dividing the marked first standard data set into a training set, a verification set and a test set;
The first generation unit is used for training the long-period memory network model based on the training set, obtaining the weight and the bias of the long-period memory network model and generating a first movement capacity assessment model;
a tenth obtaining unit configured to verify the first exercise capacity assessment model based on the verification set, and obtain a first verification result;
an eleventh obtaining unit, configured to obtain a second exercise ability evaluation model if the first verification result is verification passed;
a twelfth obtaining unit, configured to train the first exercise capacity assessment model if the first verification result is not passed, until the first verification result is passed, to obtain the second exercise capacity assessment model;
a thirteenth obtaining unit configured to test the second exercise capacity assessment model based on the test set, to obtain the first target exercise capacity assessment model.
Further, the system includes:
the third construction unit is used for constructing an expert system based on the professional field knowledge base;
A fourteenth obtaining unit, configured to send the exercise capability assessment result to the expert system, and perform a level assessment on the exercise capability assessment result to obtain a first real-time level;
a fifteenth obtaining unit configured to obtain first sports item information based on the first real-time level.
Further, the system includes:
a sixteenth obtaining unit for obtaining a first time period and a preset evaluation frequency based on the first sports item information;
a seventeenth obtaining unit, configured to perform, in the first time period, exercise capability assessment on the second user according to the preset assessment frequency, to obtain an exercise capability assessment curve;
an eighteenth obtaining unit, configured to perform health assessment on the second user in the first time period, to obtain a health assessment curve;
a nineteenth obtaining unit configured to perform curve fitting on the exercise ability evaluation curve and the health evaluation curve to obtain a first fitted curve;
The first evaluation unit is used for evaluating the movement effect of the second user based on the first fitting curve.
Further, the system includes:
the first acquisition unit is used for acquiring second user attribute information;
the twentieth obtaining unit is used for carrying out feature analysis on the second user attribute information and the first fitting curve according to the expert system to obtain a first analysis result;
a twenty-first obtaining unit, configured to obtain a first adjustment instruction according to the first analysis result;
the first execution unit is used for adjusting the first sports item information based on the first adjustment instruction.
Further, the system includes:
a twenty-second obtaining unit, configured to obtain a preset motion environment temperature threshold range;
a twenty-third obtaining unit, configured to obtain an actual moving environment temperature, and obtain a second adjustment instruction if the actual moving environment temperature does not meet the preset moving environment temperature threshold range;
And the second execution unit is used for adjusting the first sports item information based on the second adjustment instruction.
Exemplary electronic device
The electronic device of the present application is described below with reference to figure 6,
based on the same inventive concept as the exercise capacity assessment method of a chronic kidney disease patient in the foregoing embodiments, the present application also provides a system for exercise capacity assessment of a chronic kidney disease patient, including: a processor coupled to a memory for storing a program that, when executed by the processor, causes the system to perform the method of any of the first aspects.
The electronic device 300 includes: a processor 302, a communication interface 303, a memory 301. Optionally, the electronic device 300 may also include a bus architecture 304. Wherein the communication interface 303, the processor 302 and the memory 301 may be interconnected by a bus architecture 304; the bus architecture 304 may be a peripheral component interconnect (peripheral component interconnect, PCI) bus, or an extended industry standard architecture (extended industry Standard architecture, EISA) bus, among others. The bus architecture 304 may be divided into address buses, data buses, control buses, and the like. For ease of illustration, only one thick line is shown in fig. 6, but not only one bus or one type of bus.
The communication interface 303 uses any transceiver-like means for communicating with other devices or communication networks, such as ethernet, radio access network (radio access network, RAN), wireless local area network (wireless local area networks, WLAN), wired access network, etc.
The memory 301 may be, but is not limited to, ROM or other type of static storage device that may store static information and instructions, RAM or other type of dynamic storage device that may store information and instructions, or may be an EEPROM (electrically erasable Programmable read-only memory), a compact disc-only memory (CD-ROM) or other optical disk storage, optical disk storage (including compact disc, laser disc, optical disc, digital versatile disc, blu-ray disc, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. The memory may be self-contained and coupled to the processor through bus architecture 304. The memory may also be integrated with the processor.
The memory 301 is used for storing computer-executable instructions for executing the embodiments of the present application, and is controlled by the processor 302 to execute the instructions. The processor 302 is configured to execute computer-executable instructions stored in the memory 301, thereby implementing a method for evaluating exercise ability of a patient with chronic kidney disease according to the above-described embodiments of the present application.
Alternatively, the computer-executable instructions in the present application may be referred to as application code, which is not specifically limited in this application.
The application provides a method for evaluating the exercise capacity of a patient with chronic kidney disease, wherein the method comprises the following steps: performing a first exercise item test on a first user based on the exercise test index set to obtain a first standard data set; acquiring first user health information, training a long-term memory network model based on the first standard data set and the first user health information, and constructing a first target exercise capacity assessment model; performing a second exercise item test on the first user based on the exercise test index set to obtain a second standard data set; training the long-term and short-term memory network model based on the second standard data set and the first user health information, and constructing a second target movement capacity assessment model; extracting parameters of the first target movement capacity assessment model to obtain first model parameters, and extracting parameters of the second target movement capacity assessment model to obtain second model parameters; updating the long-term and short-term memory network model according to the first model parameter and the second model parameter to obtain a third target movement capacity evaluation model; and carrying out exercise capacity evaluation on the second user according to the third target exercise capacity evaluation model to obtain an exercise capacity evaluation result.
Those of ordinary skill in the art will appreciate that: the various numbers of first, second, etc. referred to in this application are merely for ease of description and are not intended to limit the scope of this application nor to indicate any order. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one" means one or more. At least two means two or more. "at least one," "any one," or the like, refers to any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one of a, b, or c (species ) may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or plural.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the present application are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device including one or more servers, data centers, etc. that can be integrated with the available medium. The usable medium may be a magnetic medium (e.g., a floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), etc.
The various illustrative logical units and circuits described herein may be implemented or performed with a general purpose processor, a digital signal processor, an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, but in the alternative, the general purpose processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a digital signal processor and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a digital signal processor core, or any other similar configuration.
The steps of a method or algorithm described in the present application may be embodied directly in hardware, in a software element executed by a processor, or in a combination of the two. The software elements may be stored in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. In an example, a storage medium may be coupled to the processor such that the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC, which may reside in a terminal. In the alternative, the processor and the storage medium may reside in different components in a terminal. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Although the present application has been described in connection with specific features and embodiments thereof, it will be apparent that various modifications and combinations can be made without departing from the spirit and scope of the application. Accordingly, the specification and drawings are merely exemplary illustrations of the present application as defined in the appended claims and are considered to cover any and all modifications, variations, combinations, or equivalents that fall within the scope of the present application. It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims and the equivalents thereof, the present application is intended to include such modifications and variations.
Claims (6)
1. A method of assessing motor capacity in a patient suffering from chronic kidney disease, the method comprising:
performing a first exercise item test on a first user based on the exercise test index set to obtain a first standard data set;
the first user is not particularly specific to a certain user, and is a plurality of patients suffering from chronic kidney disease;
acquiring first user health information, training a long-term memory network model based on the first standard data set and the first user health information, and constructing a first target exercise capacity assessment model;
Performing a second exercise item test on the first user based on the exercise test index set to obtain a second standard data set;
training the long-term and short-term memory network model based on the second standard data set and the first user health information, and constructing a second target movement capacity assessment model;
extracting parameters of the first target movement capacity assessment model to obtain first model parameters, and extracting parameters of the second target movement capacity assessment model to obtain second model parameters;
updating the long-term and short-term memory network model according to the first model parameter and the second model parameter to obtain a third target movement capacity evaluation model;
performing exercise capacity assessment on the second user according to the third target exercise capacity assessment model to obtain an exercise capacity assessment result;
the first exercise item test is carried out on the first user based on the exercise test index set to obtain a first standard data set, and the method further comprises the following steps:
constructing the exercise test index set, wherein the exercise test index set comprises heart rate, blood pressure, maximum oxygen uptake, blood sugar and subjective fatigue degree;
performing the first exercise item test on the first user based on the exercise test index set, and acquiring time sequence data to obtain a first test data set;
Performing data cleaning and normalization processing on the first test data set to obtain the first standard data set;
the obtaining the first user health information, training a long-term memory network model based on the first standard data set and the first user health information, and constructing a first target movement capacity assessment model, and further comprising:
obtaining the long-term and short-term memory network model;
the first user health information is used as identification information, the first standard data set is identified, and the identified first standard data set is divided into a training set, a verification set and a test set;
training the long-period memory network model based on the training set to obtain the weight and bias of the long-period memory network model, and generating a first exercise capacity assessment model;
verifying the first movement capability assessment model based on the verification set to obtain a first verification result;
if the first verification result is that the verification is passed, a second motion capability assessment model is obtained;
if the first verification result is not passed, training the first movement capacity assessment model until the first verification result is passed, and obtaining the second movement capacity assessment model;
Testing the second exercise capacity assessment model based on the test set to obtain the first target exercise capacity assessment model;
and performing exercise capacity evaluation on a second user according to the third target exercise capacity evaluation model to obtain an exercise capacity evaluation result, and then further comprising:
constructing an expert system based on the expert domain knowledge base;
transmitting the exercise capacity assessment result to the expert system, and carrying out grade assessment on the exercise capacity assessment result to obtain a first real-time grade;
and obtaining first sports item information based on the first real-time level.
2. The method of claim 1, wherein the obtaining the first athletic item information based on the first real-time level, thereafter, further comprises:
acquiring a first time period and a preset evaluation frequency based on the first sports item information;
in the first time period, carrying out movement capacity assessment on the second user according to the preset assessment frequency to obtain a movement capacity assessment curve;
in the first time period, carrying out health assessment on the second user to obtain a health assessment curve;
Performing curve fitting on the exercise capacity evaluation curve and the health evaluation curve to obtain a first fitted curve;
and evaluating the movement effect of the second user based on the first fitting curve.
3. The method of claim 2, wherein the method further comprises:
collecting second user attribute information;
performing feature analysis on the second user attribute information and the first fitting curve according to the expert system to obtain a first analysis result;
obtaining a first adjustment instruction according to the first analysis result;
and adjusting the first sports item information based on the first adjustment instruction.
4. A method as claimed in claim 3, wherein the method further comprises:
obtaining a preset motion environment temperature threshold range;
acquiring an actual movement environment temperature, and acquiring a second adjustment instruction if the actual movement environment temperature does not meet the preset movement environment temperature threshold range;
and adjusting the first sports item information based on the second adjustment instruction.
5. A motor ability assessment system for a patient with chronic kidney disease, the system comprising:
the first obtaining unit is used for carrying out a first sports item test on a first user based on the sports test index set to obtain a first standard data set;
The second obtaining unit is used for obtaining first user health information, training a long-term memory network model based on the first standard data set and the first user health information, and constructing a first target movement capacity assessment model;
the third obtaining unit is used for carrying out a second exercise project test on the first user based on the exercise test index set to obtain a second standard data set;
the first construction unit is used for training the long-period memory network model based on the second standard data set and the first user health information, and constructing a second target movement capacity assessment model;
the fourth obtaining unit is used for extracting parameters of the first target movement capacity assessment model to obtain first model parameters, and extracting parameters of the second target movement capacity assessment model to obtain second model parameters;
a fifth obtaining unit, configured to update the long-short-term memory network model according to the first model parameter and the second model parameter, to obtain a third target movement ability evaluation model;
The sixth obtaining unit is used for carrying out exercise capacity assessment on the second user according to the third target exercise capacity assessment model to obtain an exercise capacity assessment result;
the second construction unit is used for constructing the exercise test index set, and the exercise test index set comprises heart rate, blood pressure, maximum oxygen uptake, blood sugar and subjective fatigue degree;
a seventh obtaining unit, configured to perform the first exercise item test on the first user based on the exercise test index set, collect time-series data, and obtain a first test data set;
an eighth obtaining unit, configured to perform data cleaning and normalization processing on the first test data set, to obtain the first standard data set;
a ninth obtaining unit, configured to obtain the long-short-period memory network model;
the first dividing unit is used for marking the first standard data set by taking the first user health information as marking information and dividing the marked first standard data set into a training set, a verification set and a test set;
The first generation unit is used for training the long-period memory network model based on the training set, obtaining the weight and the bias of the long-period memory network model and generating a first movement capacity assessment model;
a tenth obtaining unit configured to verify the first exercise capacity assessment model based on the verification set, and obtain a first verification result;
an eleventh obtaining unit, configured to obtain a second exercise ability evaluation model if the first verification result is verification passed;
a twelfth obtaining unit, configured to train the first exercise capacity assessment model if the first verification result is not passed, until the first verification result is passed, to obtain the second exercise capacity assessment model;
a thirteenth obtaining unit configured to test the second exercise capacity assessment model based on the test set, to obtain the first target exercise capacity assessment model;
the third construction unit is used for constructing an expert system based on the professional field knowledge base;
A fourteenth obtaining unit, configured to send the exercise capability assessment result to the expert system, and perform a level assessment on the exercise capability assessment result to obtain a first real-time level;
a fifteenth obtaining unit configured to obtain first sports item information based on the first real-time level.
6. A system for exercise capacity assessment of a patient with chronic kidney disease comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method of any one of claims 1 to 4 when the program is executed by the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111579428.2A CN114255873B (en) | 2021-12-22 | 2021-12-22 | Exercise capacity assessment method and system for chronic kidney disease patient |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111579428.2A CN114255873B (en) | 2021-12-22 | 2021-12-22 | Exercise capacity assessment method and system for chronic kidney disease patient |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114255873A CN114255873A (en) | 2022-03-29 |
| CN114255873B true CN114255873B (en) | 2023-04-28 |
Family
ID=80794205
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111579428.2A Active CN114255873B (en) | 2021-12-22 | 2021-12-22 | Exercise capacity assessment method and system for chronic kidney disease patient |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114255873B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115564617A (en) * | 2022-10-20 | 2023-01-03 | 宁波浙鼎教育科技有限公司 | Digital sports evaluation management system |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100030574A1 (en) * | 2008-08-04 | 2010-02-04 | Coe Fredric L | Clinical Laboratory-Based Disease Management Program, With Automated Patient-Specific Treatment Advice |
| CN104083174A (en) * | 2014-05-23 | 2014-10-08 | 奥美之路(北京)技术顾问有限公司 | Exercise ability evaluation model |
| CN105205765A (en) * | 2015-07-08 | 2015-12-30 | 奥美之路(北京)健康科技股份有限公司 | Old people exercise ability evaluation model |
| CN105975773A (en) * | 2016-05-05 | 2016-09-28 | 武汉哈福科技有限公司 | Chronic disease health management system and method |
| CN107169269A (en) * | 2017-04-24 | 2017-09-15 | 广东健凯医疗有限公司 | Fitness campaign capability evaluation system and method |
| CN107595308A (en) * | 2017-08-29 | 2018-01-19 | 中科院合肥技术创新工程院 | A kind of EOM functional assessment and training system |
| CN111724897B (en) * | 2020-06-12 | 2022-07-01 | 电子科技大学 | Motion function data processing method and system |
-
2021
- 2021-12-22 CN CN202111579428.2A patent/CN114255873B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN114255873A (en) | 2022-03-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102008196B1 (en) | Apparatus for generating of Potassium level determination model using ECG and method thereof | |
| CN108970085B (en) | Method, apparatus and storage medium for analyzing physical performance of exercise | |
| CN108601566B (en) | Mental stress evaluation method and device | |
| US20090326407A1 (en) | Electrophysiological Analysis System and Method | |
| US20190175091A1 (en) | System and method for classification and quantitative estimation of cognitive stress | |
| CN111508607B (en) | Obesity prediction system based on BP neural network | |
| CN114255873B (en) | Exercise capacity assessment method and system for chronic kidney disease patient | |
| De Brabandere et al. | Data fusion of body-worn accelerometers and heart rate to predict VO2max during submaximal running | |
| CN113171080B (en) | Energy metabolism evaluation method and system based on wearable sensing information fusion | |
| CN112582067A (en) | Age estimation model training and age estimation method and device based on big data | |
| Kim et al. | Modeling long-term human activeness using recurrent neural networks for biometric data | |
| CN111544853A (en) | Physical index evaluation method and equipment in running exercise | |
| e Silva et al. | Prediction of mortality in coronary artery disease: role of machine learning and maximal exercise capacity | |
| WO2019084802A1 (en) | Method and system for detecting noise in vital sign signal | |
| Sharma et al. | Artificial neural network classification models for stress in reading | |
| Lin et al. | Intelligent exercise guidance system based on smart clothing | |
| CN116434979A (en) | Physiological state cloud monitoring method, monitoring system and storage medium | |
| Hsiao et al. | Usability of wearable devices with a novel cardiac force index for estimating the dynamic cardiac function: Observational study | |
| JP2022133922A (en) | Biological information calculation system | |
| Imbach et al. | Training load responses modelling in elite sports: how to deal with generalisation? | |
| Neshitov et al. | Estimation of cardiorespiratory fitness using heart rate and step count data | |
| Vyas et al. | Power Saving Approach of a Smart Watch for Monitoring the Heart Rate of a Runner | |
| US20240016396A1 (en) | Biometric information computing system | |
| Erdogan et al. | Non-invasive detection of the anaerobic threshold by a neural network model of the heart rate—work rate relationship | |
| CN115736915B (en) | Patient physical ability assessment method based on multi-source information fusion |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |