CN110164524A - A kind of hemiplegia patient training mission adaptive matching method and its system - Google Patents
A kind of hemiplegia patient training mission adaptive matching method and its system Download PDFInfo
- Publication number
- CN110164524A CN110164524A CN201910356380.5A CN201910356380A CN110164524A CN 110164524 A CN110164524 A CN 110164524A CN 201910356380 A CN201910356380 A CN 201910356380A CN 110164524 A CN110164524 A CN 110164524A
- Authority
- CN
- China
- Prior art keywords
- rehabilitation training
- decision tree
- sample
- tree model
- adaptive
- 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.)
- Pending
Links
- 238000012549 training Methods 0.000 title claims abstract description 156
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000003044 adaptive effect Effects 0.000 title claims abstract description 34
- 206010019468 Hemiplegia Diseases 0.000 title claims abstract description 18
- 238000003066 decision tree Methods 0.000 claims abstract description 56
- 239000000523 sample Substances 0.000 claims description 50
- 238000000605 extraction Methods 0.000 claims description 16
- 230000000638 stimulation Effects 0.000 claims description 15
- 238000012360 testing method Methods 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 230000005021 gait Effects 0.000 claims description 7
- 239000013610 patient sample Substances 0.000 claims description 7
- 230000003902 lesion Effects 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 230000001133 acceleration Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000003183 myoelectrical effect Effects 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 abstract description 3
- 241001269238 Data Species 0.000 abstract 1
- 230000006378 damage Effects 0.000 description 4
- 208000027418 Wounds and injury Diseases 0.000 description 2
- 208000026106 cerebrovascular disease Diseases 0.000 description 2
- 208000014674 injury Diseases 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 230000036772 blood pressure Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000004064 dysfunction Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000002560 therapeutic procedure Methods 0.000 description 1
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
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/30—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Physical Education & Sports Medicine (AREA)
- Engineering & Computer Science (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a kind of hemiplegia patient training mission adaptive matching methods, after the sample case history and corresponding rehabilitation training strategy for acquiring a large amount of hemiplegic patients, by preliminary Data Analysis Services, form the case database and rehabilitation training template library of the hemiplegic patient by mark, rehabilitation training Adaptive matching decision tree is constructed by these sample datas later, in actual rehabilitation, it, can the rehabilitation training template that is adapted therewith of Auto-matching by the decision-tree model established using the personal data of patient as input.The present invention can effectively reduce the time of making a plan, and more scientifically hemiplegic patient be helped to carry out rehabilitation training.
Description
Technical Field
The invention relates to the technical field of rehabilitation training of hemiplegic patients, in particular to a self-adaptive matching method and a self-adaptive matching system for a rehabilitation training task of a hemiplegic patient.
Background
With the increasing incidence of cerebrovascular diseases, the disability rate of cerebrovascular diseases has become a focus of attention in the medical field and even the whole society. How to help hemiplegia patients return to normal life in the early days is a problem of great attention in the whole society. The causes of hemiplegia patients are numerous, and the types of hemiplegia vary according to the characteristics of each patient. Therefore, it is necessary to study the rehabilitation law of limb movement dysfunction and the characteristics of patients according to the individual rehabilitation training requirements of hemiplegic patients, design a rehabilitation training mode and task matched with physiological signals and gait characteristics, and realize adaptive matching of the rehabilitation training task integrating training, feedback and evaluation.
The existing rehabilitation training process generally comprises the steps that a doctor formulates a rehabilitation training task according to the condition of a patient and a rehabilitation training rule, the time spent is long, different medical workers make different rehabilitation training tasks due to professional level or subjective factors, and the rehabilitation effect of the patient is greatly different. Moreover, the existing rehabilitation training strategy does not fully utilize data analysis and artificial intelligence related methods to carry out statistical analysis on a large number of existing medical record samples and corresponding rehabilitation training tasks, a rehabilitation training template adaptive to the individual characteristics of the patient and the hemiplegia rehabilitation law is concluded, and online adaptive matching and iterative optimization of the rehabilitation training template are realized.
Therefore, how to provide a method and a system thereof capable of automatically matching a rehabilitation training task scheme for a hemiplegic patient is a problem to be solved urgently by those skilled in the art.
Disclosure of Invention
In view of the above, the present invention provides a method and a system for adaptive matching of a rehabilitation training task for a hemiplegic patient, wherein after a large number of sample medical records of the hemiplegic patient and corresponding rehabilitation training strategies are collected, a rehabilitation training adaptive matching decision tree is constructed through preliminary data analysis and processing, in the actual rehabilitation therapy, the personal data of the patient is used as input, and the rehabilitation training template adapted to the personal data can be automatically matched through the established decision tree model, so that medical staff can be effectively reduced.
In order to achieve the purpose, the invention adopts the following technical scheme:
a self-adaptive matching method for a rehabilitation training task of a hemiplegic patient comprises the following steps:
generating a rehabilitation training task self-adaptive decision tree model: collecting a hemiplegia patient sample with a label, extracting corresponding parameters of sample characteristics to form a sample set, thereby generating a rehabilitation training task self-adaptive decision tree model, and further verifying the accuracy of the self-adaptive matching method decision tree model;
automatically matching a rehabilitation training template for a hemiplegic patient without a label: and inputting the characteristic information of the hemiplegic patient without the label into the rehabilitation training task self-adaptive decision tree model to obtain a judgment result.
Preferably, the method further comprises the following steps: updating the rehabilitation training task self-adaptive decision tree model: updating the labeled hemiplegic patient sample, thereby updating the rehabilitation training task adaptive decision tree model.
Preferably, the sample characteristics include: demographic profile characteristics, clinical characteristics, and physiological parameters;
the demographic characteristics include gender and age;
the clinical characteristics include lesion grade and lesion time;
the physiological parameters comprise kinematic parameters, kinetic parameters, myoelectric parameters, electroencephalogram parameters and energy parameters.
Preferably, the rehabilitation training template comprises: training tasks and specific control parameters suitable for patients;
the control parameters include: training movement mode, single limb movement parameter, gait planning parameter and electrical stimulation parameter;
the trained motion patterns comprise: active, passive, assisted and impedance;
the single limb movement parameters include: the speed and acceleration of movement of a single limb;
the gait planning parameters include: a standing phase, a stepping phase and a double-support phase;
the electrical stimulation parameters include: the electrical stimulation intensity, the electrical stimulation part and the electrical stimulation time-frequency parameters.
Preferably, the specific content of the generation of the rehabilitation training task adaptive decision tree model includes:
(1) preparing data: collecting sample characteristics of the hemiplegia patient with the label, performing parameter extraction aiming at different sample characteristics to form a sample set, and dividing the sample set into a training set and a testing set;
(2) generating a rehabilitation training task self-adaptive decision tree model: training the training sets respectively according to different sample characteristics to generate the rehabilitation training task adaptive decision tree model;
(3) verifying the accuracy of the adaptive matching method decision tree model: inputting the test set into the rehabilitation training task self-adaptive decision tree model to obtain a judgment result, and comparing the judgment result with an actual training task to judge the accuracy.
Preferably, the step (2) specifically comprises:
and calculating the experience entropy of the training set according to sample data in the training set, calculating the experience condition entropy of the training set and calculating the information gain of different characteristics aiming at different calculation characteristics, further calculating the information gain rate, generating a rehabilitation training task self-adaptive decision tree model by adopting a C4.5 algorithm, and selecting the characteristic with the maximum information gain rate in the C4.5 algorithm for splitting.
Preferably, the specific content of the updating of the rehabilitation training task adaptive decision tree model includes:
and when the sample of the hemiplegic patient with the label continuously changes, updating the property and the type of each node of the rehabilitation training task self-adaptive decision tree model, and continuously iterating, training and correcting the node, the structure and the threshold of the rehabilitation training task self-adaptive decision tree model.
A hemiplegia patient rehabilitation training task adaptive matching system, comprising: the system comprises an information extraction module, a data training module, a model verification module and a sample adding module;
the information extraction module is used for extracting corresponding parameters aiming at different sample characteristics to form a sample set, and dividing the sample set into a training set and a testing set;
the data training module is connected with the information extraction module and used for training the training set to obtain a rehabilitation training task self-adaptive decision tree model;
the model verification module is connected with the information extraction module and the data training module and is used for verifying the accuracy of the rehabilitation training task adaptive decision tree model through the test set;
and the sample adding module is connected with the information extracting module and is used for adding new sample parameters.
It should be noted that: the hemiplegic patient with the label is a hemiplegic patient who has already made a training task and is used for collecting sample data, and the hemiplegic patient without the label is a patient who needs to be further matched with the training task through the method or the system.
According to the technical scheme, compared with the prior art, the hemiplegia patient rehabilitation training task adaptive matching method and system select classified features and attributes by using the information gain rate, and overcome the defect that the features are selected by using the information gain, namely the latter is easy to select the features with a large number of values; the method used by the invention can complete discretization processing of continuous attributes, for example, data preprocessing of some continuous physiological parameters, discretization of the parameters can be carried out, and the parameters are changed into input types according with the method;
the invention can process the attribute characteristics of the data type and the conventional type at the same time, and can train a large number of data sources in a relatively short time, thereby obtaining accurate and reliable results; the method is insensitive to the missing value or the abnormal value, can process irrelevant characteristic data, has high efficiency, only needs to construct the decision tree once, and can be used repeatedly. In addition, in the use process, if the existing hemiplegic patient rehabilitation training template can not meet the rehabilitation requirement, the types of the rehabilitation training templates can be increased, and the structure and the performance of the method can be gradually optimized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of a method provided by the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention discloses a self-adaptive matching method for a rehabilitation training task of a hemiplegic patient, which comprises the following steps:
generating a rehabilitation training task self-adaptive decision tree model: collecting a hemiplegia patient sample with a label, extracting corresponding parameters of sample characteristics to form a sample set, thereby generating a rehabilitation training task self-adaptive decision tree model, and further verifying the accuracy of the self-adaptive matching method decision tree model;
wherein the sample features include: demographic profile characteristics, clinical characteristics, and physiological parameters;
demographic characteristics include gender and age;
clinical features include lesion grade and time of lesion;
the physiological parameters comprise kinematic parameters, kinetic parameters, myoelectric parameters, electroencephalogram parameters and energy parameters;
automatically matching a rehabilitation training template for a hemiplegic patient without a label: inputting the characteristic information of the hemiplegic patient without a label into a rehabilitation training task self-adaptive decision tree model to obtain a judgment result;
still further, the rehabilitation training template comprises: training tasks and specific control parameters suitable for patients;
the control parameters include: training movement mode, single limb movement parameter, gait planning parameter and electrical stimulation parameter;
the exercise patterns of training include: active, passive, assisted and impedance;
the single limb movement parameters include: the speed and acceleration of movement of a single limb;
the gait planning parameters include: a standing phase, a stepping phase and a double-support phase;
the electrical stimulation parameters include: the electrical stimulation intensity, the electrical stimulation part and the electrical stimulation time-frequency parameters.
It should be noted that: the control parameters are mainly used for controlling the hemiplegic patients to carry out rehabilitation training, and particularly and accurately guiding the rehabilitation training process of the patients, and the control parameters represent the specific details of the rehabilitation process.
Further, the updating of the rehabilitation training task adaptive decision tree model: and updating the hemiplegic patient sample with the label, thereby updating the rehabilitation training task self-adaptive decision tree model.
Furthermore, the specific content of the generation of the rehabilitation training task adaptive decision tree model includes:
(1) preparing data: collecting sample characteristics of the hemiplegia patient with the label, performing parameter extraction aiming at different sample characteristics to form a sample set, and dividing the sample set into a training set and a testing set;
(2) generating a rehabilitation training task self-adaptive decision tree model: training the training sets respectively according to different sample characteristics to generate a rehabilitation training task self-adaptive decision tree model;
(3) verifying the accuracy of the adaptive matching method decision tree model: and inputting the test set into a rehabilitation training task self-adaptive decision tree model to obtain a judgment result, and comparing the judgment result with an actual training task to judge the accuracy.
Further, the step (2) specifically includes:
the method comprises the steps of calculating the experience entropy of a training set according to sample data in the training set, calculating the experience condition entropy of the training set and calculating information gains of different features according to different calculation features, further calculating an information gain rate, generating a rehabilitation training task self-adaptive decision tree model by adopting a C4.5 algorithm, and selecting the feature with the largest information gain rate in the C4.5 algorithm for splitting.
Furthermore, the specific contents of the updating of the rehabilitation training task adaptive decision tree model include:
and when the sample of the hemiplegic patient with the label continuously changes, updating the property and the type of each node of the rehabilitation training task self-adaptive decision tree model, and continuously iterating, training and correcting the node, the structure and the threshold of the rehabilitation training task self-adaptive decision tree model.
The three large Features described above (9 small Features in total) are labeled.
Feature1＝F1＝{F11，F12}＝{A1，A2}
Feature2＝F2＝{F21，F22}＝{A3，A4}
Feature3＝F3＝{F31，F32，F33，F34，F35}＝{A5，A6，A7，A8，A9}
Note:
F1: demographic data characteristics;
F2: clinical features;
F3: a physiological parameter characteristic;
F11，A1: GenderFeature, gender feature;
F12，A2: age feature;
F21，A3: damagegardmeeature, damage level feature;
F22，A4: DamageTimeFeature, damage time characteristics;
F31，A5: kinematical parameters features, { time T, distance S, space-time TS };
F32，A6: kinetic parameter characteristics, { ground reaction force F, moment M };
F33，A7：EEGfeature，electroencephalogram signal characteristics;
F34，A8: EMGfeature, electromyographic signal features;
F35，A9: EnergyParameters, energy parameter features, { heart rate R, blood pressure BP, blood oxygen BO, physiological wasting index PCI };
the collected training data D of the hemiplegic patient is set, wherein a rehabilitation training template made by medical staff is already included. And | D | represents the total number of the acquired patient medical records, namely the number of training samples. According to the injury position and the injury intensity of the hemiplegic patient, the collected patient data and the corresponding rehabilitation training templates formulated by doctors and patients are divided into k types, and each template comprises a training task adaptive to the patient and specific control parameters.
Let k be CkClass, K ═ 1, 2, …, K, | CkIs of class CkAnd satisfyLet a certain characteristic AjIs to divide D into n subsets D1，D2，…，Dn，|DiL is DiAnd satisfyMemory set DiIn (C)kIs DikI.e. Dik＝Di∩Dk，|DikL is DikNumber of patient samples.
The empirical entropy h (D) of a given hemiplegic patient data set D is calculated:
calculating the characteristic AjEmpirical conditional entropy H (D | a) for a given hemiplegic patient data set D:
calculating a corresponding certain characteristic AjInformation gain g (D, a):
g(D，A)＝H(D)-H(D|A)
calculating corresponding characteristics AjInformation gain ratio g ofR(D，A)：
Wherein,
the iteration steps of the C4.5 algorithm are specifically as follows:
(1) if all instances in D belong to the same class CkThen set T as single junction tree and set CkReturning T as the node of the tree;
(2) if A is an empty set, T is set as a single node tree, and the class C with the largest instance tree in D is set askReturning T as the class of the node;
(3) otherwise, calculate feature Aj(AjJ-1, 2, …, l, where l is feature ajNumber of values) of the features to D, the information gain is selected so that the largest feature a is obtainedg；
(4) If A isgIf the information gain ratio of (D) is less than the threshold value epsilon, setting T as a single-node tree and setting the class C with the largest instance tree in D as the class CkReturning T as the class of the node;
(5) otherwise, for AgEach possible value a ofiIn sequence Ag＝aiPartitioning D into subsets of non-nullsDiD isiThe middle instance number and the maximum class are used as marks to construct child nodes, the nodes and the child nodes form a number T, and the T is returned;
(6) for node i, with DiThe training set for hemiplegic patients is A- { AgRecursively calling the steps (1) to (5) to obtain a subtree TiGo back to Ti。
It should be noted that: some training parameters in the training task template obtained by the method of the invention for the hemiplegia patient are further determined by medical care personnel;
a hemiplegia patient rehabilitation training task adaptive matching system, comprising: the system comprises an information extraction module, a data training module, a model verification module and a sample adding module;
the information extraction module is used for extracting corresponding parameters aiming at different sample characteristics to form a sample set, and dividing the sample set into a training set and a testing set;
the data training module is connected with the information extraction module and used for training the training set to obtain a rehabilitation training task self-adaptive decision tree model;
the model verification module is connected with the information extraction module and the data training module and used for verifying the accuracy of the rehabilitation training task self-adaptive decision tree model through the test set;
and the sample adding module is connected with the information extraction module and is used for adding new sample parameters.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. A hemiplegic patient rehabilitation training task self-adaptive matching method is characterized by comprising the following steps:
generating a rehabilitation training task self-adaptive decision tree model: collecting a hemiplegia patient sample with a label, extracting corresponding parameters of sample characteristics to form a sample set, thereby generating a rehabilitation training task self-adaptive decision tree model, and further verifying the accuracy of the self-adaptive matching method decision tree model;
automatically matching a rehabilitation training template for a hemiplegic patient without a label: and inputting the characteristic information of the hemiplegic patient without the label into the rehabilitation training task self-adaptive decision tree model to obtain a matched rehabilitation training template.
2. The adaptive matching method for the rehabilitation training task of the hemiplegic patient according to claim 1, further comprising the steps of:
updating the rehabilitation training task self-adaptive decision tree model: updating the labeled hemiplegic patient sample, thereby updating the rehabilitation training task adaptive decision tree model.
3. The adaptive matching method for rehabilitation training task of hemiplegia patient as claimed in claim 1,
the sample features include: demographic profile characteristics, clinical characteristics, and physiological parameters;
the demographic characteristics include gender and age;
the clinical characteristics include lesion grade and lesion time;
the physiological parameters comprise kinematic parameters, kinetic parameters, myoelectric parameters, electroencephalogram parameters and energy parameters.
4. The adaptive matching method for rehabilitation training task of hemiplegic patient according to claim 1, wherein said rehabilitation training template comprises: training tasks and specific control parameters suitable for patients;
the control parameters include: training movement mode, single limb movement parameter, gait planning parameter and electrical stimulation parameter;
the trained motion patterns comprise: active, passive, assisted and impedance;
the single limb movement parameters include: the speed and acceleration of movement of a single limb;
the gait planning parameters include: a standing phase, a stepping phase and a double-support phase;
the electrical stimulation parameters include: the electrical stimulation intensity, the electrical stimulation part and the electrical stimulation time-frequency parameters.
5. The adaptive matching method for the rehabilitation training task of the hemiplegic patient according to claim 1, wherein the specific content of the generation of the adaptive decision tree model for the rehabilitation training task comprises:
(1) preparing data: collecting sample characteristics of the hemiplegia patient with the label, performing parameter extraction aiming at different sample characteristics to form a sample set, and dividing the sample set into a training set and a testing set;
(2) generating a rehabilitation training task self-adaptive decision tree model: training the training sets respectively according to different sample characteristics to generate the rehabilitation training task adaptive decision tree model;
(3) verifying the accuracy of the adaptive matching method decision tree model: inputting the test set into the rehabilitation training task self-adaptive decision tree model to obtain a matched rehabilitation training template, and comparing a matching result with an actual training task to judge the accuracy.
6. The adaptive matching method for the rehabilitation training task of the hemiplegic patient according to claim 5, wherein the step (2) specifically comprises:
and calculating the experience entropy of the training set according to sample data in the training set, calculating the experience condition entropy of the training set and calculating the information gain of different characteristics aiming at different calculation characteristics, further calculating the information gain rate, generating a rehabilitation training task self-adaptive decision tree model by adopting a C4.5 algorithm, and selecting the characteristic with the maximum information gain rate in the C4.5 algorithm for splitting.
7. The adaptive matching method for the rehabilitation training task of the hemiplegic patient according to claim 2, wherein the specific contents of the updating of the adaptive decision tree model for the rehabilitation training task comprise:
and when the sample of the hemiplegic patient with the label continuously changes, updating the property and the type of each node of the rehabilitation training task self-adaptive decision tree model, and continuously iterating, training and correcting the node, the structure and the threshold of the rehabilitation training task self-adaptive decision tree model.
8. A hemiplegia patient rehabilitation training task self-adaptation matching system which is characterized by comprising: the system comprises an information extraction module, a data training module, a model verification module and a sample adding module;
the information extraction module is used for extracting corresponding parameters aiming at different sample characteristics to form a sample set, and dividing the sample set into a training set and a testing set;
the data training module is connected with the information extraction module and used for training the training set to obtain a rehabilitation training task self-adaptive decision tree model;
the model verification module is connected with the information extraction module and the data training module and is used for verifying the accuracy of the rehabilitation training task adaptive decision tree model through the test set;
and the sample adding module is connected with the information extracting module and is used for adding new sample parameters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910356380.5A CN110164524A (en) | 2019-04-29 | 2019-04-29 | A kind of hemiplegia patient training mission adaptive matching method and its system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910356380.5A CN110164524A (en) | 2019-04-29 | 2019-04-29 | A kind of hemiplegia patient training mission adaptive matching method and its system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110164524A true CN110164524A (en) | 2019-08-23 |
Family
ID=67633099
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910356380.5A Pending CN110164524A (en) | 2019-04-29 | 2019-04-29 | A kind of hemiplegia patient training mission adaptive matching method and its system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110164524A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111079651A (en) * | 2019-12-17 | 2020-04-28 | 河南水滴智能技术有限公司 | Re-optimization of gait classification method |
| CN111939529A (en) * | 2020-08-25 | 2020-11-17 | 山东大学齐鲁医院 | Active rehabilitation training method and system based on muscle force measuring device |
| CN113223662A (en) * | 2021-02-03 | 2021-08-06 | 广东易生活信息科技有限公司 | Intelligent limb rehabilitation training method and system |
| CN114203275A (en) * | 2021-12-16 | 2022-03-18 | 江苏海洋大学 | Recovery state analysis system for rehabilitation training movement |
| CN117133402A (en) * | 2023-08-30 | 2023-11-28 | 广东省中医院（广州中医药大学第二附属医院、广州中医药大学第二临床医学院、广东省中医药科学院） | Method, device, equipment and readable storage medium for dynamically supervising patient rehabilitation |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101673301A (en) * | 2009-09-11 | 2010-03-17 | 广州视景医疗软件有限公司 | Automatic generation method of visual training proposal and system thereof |
| CN103392183A (en) * | 2010-12-20 | 2013-11-13 | 皇家飞利浦电子股份有限公司 | Methods and systems for identifying patients with mild cognitive impairment at risk of converting to alzheimer's |
| CN104915560A (en) * | 2015-06-11 | 2015-09-16 | 万达信息股份有限公司 | Method for disease diagnosis and treatment scheme based on generalized neural network clustering |
| US20150269336A1 (en) * | 2014-03-24 | 2015-09-24 | Beijing University Of Technology | method for selecting features of EEG signals based on decision tree |
| CN105455976A (en) * | 2015-11-20 | 2016-04-06 | 安宁 | Intelligent rehabilitation wheelchair |
| CN105793852A (en) * | 2013-12-04 | 2016-07-20 | M·奥利尼克 | Computational medical treatment plan method and system with mass medical analysis |
| CN105912846A (en) * | 2016-04-07 | 2016-08-31 | 南京小网科技有限责任公司 | Intelligent medical aid decision making system on basis of cloud computing technique and medical knowledge base technique |
| WO2016192612A1 (en) * | 2015-06-02 | 2016-12-08 | 陈宽 | Method for analysing medical treatment data based on deep learning, and intelligent analyser thereof |
| CN106779084A (en) * | 2016-09-30 | 2017-05-31 | 广州英康唯尔互联网服务有限公司 | Machine learning system and method |
| CN106778042A (en) * | 2017-01-26 | 2017-05-31 | 中电科软件信息服务有限公司 | Cardio-cerebral vascular disease patient similarity analysis method and system |
| CN107485844A (en) * | 2017-09-27 | 2017-12-19 | 广东工业大学 | A kind of limb rehabilitation training method, system and embedded device |
| CN107564585A (en) * | 2017-07-06 | 2018-01-09 | 四川护理职业学院 | Brain palsy recovery management system and method based on cloud platform |
| CN107958708A (en) * | 2017-12-22 | 2018-04-24 | 北京鑫丰南格科技股份有限公司 | Risk trend appraisal procedure and system after institute |
| CN109065113A (en) * | 2018-07-12 | 2018-12-21 | 山东师范大学 | Human body loss of weight proposal recommending method, system and medium based on machine learning |
| CN109243561A (en) * | 2018-08-10 | 2019-01-18 | 上海交通大学 | Model optimization method and system of treatment scheme recommendation system |
| CN109543711A (en) * | 2018-10-15 | 2019-03-29 | 天津大学 | A kind of decision tree generation method based on ID3 algorithm |
| CN109616168A (en) * | 2018-12-14 | 2019-04-12 | 北京工业大学 | A kind of medical field Intelligent management model construction method based on electronic health record |
| CN109637620A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Prescription based on data analysis generates monitoring method, device, equipment and medium |
-
2019
- 2019-04-29 CN CN201910356380.5A patent/CN110164524A/en active Pending
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101673301A (en) * | 2009-09-11 | 2010-03-17 | 广州视景医疗软件有限公司 | Automatic generation method of visual training proposal and system thereof |
| CN103392183A (en) * | 2010-12-20 | 2013-11-13 | 皇家飞利浦电子股份有限公司 | Methods and systems for identifying patients with mild cognitive impairment at risk of converting to alzheimer's |
| CN105793852A (en) * | 2013-12-04 | 2016-07-20 | M·奥利尼克 | Computational medical treatment plan method and system with mass medical analysis |
| US20150269336A1 (en) * | 2014-03-24 | 2015-09-24 | Beijing University Of Technology | method for selecting features of EEG signals based on decision tree |
| WO2016192612A1 (en) * | 2015-06-02 | 2016-12-08 | 陈宽 | Method for analysing medical treatment data based on deep learning, and intelligent analyser thereof |
| CN104915560A (en) * | 2015-06-11 | 2015-09-16 | 万达信息股份有限公司 | Method for disease diagnosis and treatment scheme based on generalized neural network clustering |
| CN105455976A (en) * | 2015-11-20 | 2016-04-06 | 安宁 | Intelligent rehabilitation wheelchair |
| CN105912846A (en) * | 2016-04-07 | 2016-08-31 | 南京小网科技有限责任公司 | Intelligent medical aid decision making system on basis of cloud computing technique and medical knowledge base technique |
| CN106779084A (en) * | 2016-09-30 | 2017-05-31 | 广州英康唯尔互联网服务有限公司 | Machine learning system and method |
| CN106778042A (en) * | 2017-01-26 | 2017-05-31 | 中电科软件信息服务有限公司 | Cardio-cerebral vascular disease patient similarity analysis method and system |
| CN107564585A (en) * | 2017-07-06 | 2018-01-09 | 四川护理职业学院 | Brain palsy recovery management system and method based on cloud platform |
| CN107485844A (en) * | 2017-09-27 | 2017-12-19 | 广东工业大学 | A kind of limb rehabilitation training method, system and embedded device |
| CN107958708A (en) * | 2017-12-22 | 2018-04-24 | 北京鑫丰南格科技股份有限公司 | Risk trend appraisal procedure and system after institute |
| CN109065113A (en) * | 2018-07-12 | 2018-12-21 | 山东师范大学 | Human body loss of weight proposal recommending method, system and medium based on machine learning |
| CN109243561A (en) * | 2018-08-10 | 2019-01-18 | 上海交通大学 | Model optimization method and system of treatment scheme recommendation system |
| CN109543711A (en) * | 2018-10-15 | 2019-03-29 | 天津大学 | A kind of decision tree generation method based on ID3 algorithm |
| CN109637620A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Prescription based on data analysis generates monitoring method, device, equipment and medium |
| CN109616168A (en) * | 2018-12-14 | 2019-04-12 | 北京工业大学 | A kind of medical field Intelligent management model construction method based on electronic health record |
Non-Patent Citations (2)
| Title |
|---|
| 陈柳剑: "医院医疗质量综合分析系统关键技术研究", 《万方数据》 * |
| 韩忠明，段大高著: "《数据分析与R》", 31 August 2014 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111079651A (en) * | 2019-12-17 | 2020-04-28 | 河南水滴智能技术有限公司 | Re-optimization of gait classification method |
| CN111939529A (en) * | 2020-08-25 | 2020-11-17 | 山东大学齐鲁医院 | Active rehabilitation training method and system based on muscle force measuring device |
| CN111939529B (en) * | 2020-08-25 | 2021-10-01 | 山东大学齐鲁医院 | Active rehabilitation training method and system based on muscle force measuring device |
| CN113223662A (en) * | 2021-02-03 | 2021-08-06 | 广东易生活信息科技有限公司 | Intelligent limb rehabilitation training method and system |
| CN113223662B (en) * | 2021-02-03 | 2023-07-28 | 广东易生活信息科技有限公司 | Intelligent limb rehabilitation training method and system |
| CN114203275A (en) * | 2021-12-16 | 2022-03-18 | 江苏海洋大学 | Recovery state analysis system for rehabilitation training movement |
| CN117133402A (en) * | 2023-08-30 | 2023-11-28 | 广东省中医院（广州中医药大学第二附属医院、广州中医药大学第二临床医学院、广东省中医药科学院） | Method, device, equipment and readable storage medium for dynamically supervising patient rehabilitation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110164524A (en) | A kind of hemiplegia patient training mission adaptive matching method and its system | |
| Bird et al. | A Deep Evolutionary Approach to Bioinspired Classifier Optimisation for Brain‐Machine Interaction | |
| CN111462841B (en) | Intelligent depression diagnosis device and system based on knowledge graph | |
| Camargo et al. | Feature selection and non-linear classifiers: Effects on simultaneous motion recognition in upper limb | |
| CN110021397A (en) | Method and storage medium based on human body physiological parameter prediction dosage | |
| CN103116707A (en) | Heart disease intelligent diagnostic method based on case reasoning | |
| Zhang et al. | EMG signals based human action recognition via deep belief networks | |
| CN106955112A (en) | Brain wave Emotion recognition method based on Quantum wavelet neural networks model | |
| WO2020224433A1 (en) | Target object attribute prediction method based on machine learning and related device | |
| CN111785366B (en) | Patient treatment scheme determination method and device and computer equipment | |
| Thenmozhi et al. | Feature selection using extreme gradient boosting Bayesian optimization to upgrade the classification performance of motor imagery signals for BCI | |
| CN109805924A (en) | ECG's data compression method and cardiac arrhythmia detection system based on CNN | |
| CN115316991B (en) | Self-adaptive recognition early warning method for irritation emotion | |
| Mahmood et al. | Early detection of clinical parameters in heart disease by improved decision tree algorithm | |
| CN110687999A (en) | Method and device for semantic processing of electroencephalogram signals | |
| Tiwari et al. | Classification of physiological signals for emotion recognition using IoT | |
| CN113288157A (en) | Arrhythmia classification method based on depth separable convolution and improved loss function | |
| Sahu et al. | An improved feature selection approach using global best guided Gaussian artificial bee colony for EMG classification | |
| Pimentel et al. | Human mental state monitoring in the wild: Are we better off with deeperneural networks or improved input features? | |
| Gupta et al. | An optimal multi-disease prediction framework using hybrid machine learning techniques: 10.48129/kjs. splml. 19321 | |
| Coelho et al. | A novel sEMG data augmentation based on WGAN-GP | |
| Zhang et al. | Human movements classification using multi-channel surface EMG signals and deep learning technique | |
| Anam et al. | Classification model for diabetes mellitus diagnosis based on k-means clustering algorithm optimized with bat algorithm | |
| CN116434979A (en) | Physiological state cloud monitoring method, monitoring system and storage medium | |
| CN115273176A (en) | Pain multi-algorithm objective assessment method based on vital signs and expressions |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190823 |