CN116959723A - Evaluation and training method and system for old people falling prevention - Google Patents
Evaluation and training method and system for old people falling prevention Download PDFInfo
- Publication number
- CN116959723A CN116959723A CN202310946623.7A CN202310946623A CN116959723A CN 116959723 A CN116959723 A CN 116959723A CN 202310946623 A CN202310946623 A CN 202310946623A CN 116959723 A CN116959723 A CN 116959723A
- Authority
- CN
- China
- Prior art keywords
- training
- gait
- balance
- patient
- evaluation
- 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 86
- 238000011156 evaluation Methods 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000002265 prevention Effects 0.000 title claims abstract description 15
- 230000005021 gait Effects 0.000 claims abstract description 63
- 230000004064 dysfunction Effects 0.000 claims abstract description 30
- 238000013210 evaluation model Methods 0.000 claims abstract description 29
- 238000003745 diagnosis Methods 0.000 claims abstract description 18
- 238000012360 testing method Methods 0.000 claims abstract description 7
- 210000003141 lower extremity Anatomy 0.000 claims description 23
- 238000007637 random forest analysis Methods 0.000 claims description 12
- 230000001720 vestibular Effects 0.000 claims description 9
- 230000005856 abnormality Effects 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 4
- 238000007477 logistic regression Methods 0.000 claims description 4
- 230000004580 weight loss Effects 0.000 claims description 4
- 239000013585 weight reducing agent Substances 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 abstract description 2
- 230000008520 organization Effects 0.000 abstract description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000000546 chi-square test Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000556 factor analysis Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
Abstract
The application provides a system and a method for evaluating and training the fall prevention of the old, which are used for acquiring the self-evaluation result of the fall risk uploaded by a cloud platform and providing a pre-diagnosis suggestion; performing gait and balance tests on a patient at risk on special rehabilitation equipment, and synchronously acquiring gait and balance information of the patient; and respectively inputting the gait and balance information into a gait evaluation model and a balance evaluation model of the cloud platform, and automatically generating an individual training scheme applied to special rehabilitation equipment according to the gait and balance dysfunction degree. According to the application, a cloud hospital platform is utilized to construct a multi-community-oriented 5G remote intelligent rehabilitation system, the space and distance obstacle of a medical institution-community-site are overcome, the fall-preventing function evaluation and the standardization of a rehabilitation training program of a patient are realized according to the background calculation of the intelligent rehabilitation system, the diagnosis and treatment pressure of an upper-level hospital is relieved, and the fall-preventing rehabilitation treatment efficiency is improved; promote the patient to shunt to the community, promote basic unit's community and the recovered ability and the level of endowment organization.
Description
Technical Field
The application relates to the technical field of lower limb exercise rehabilitation, in particular to an evaluation and training method and system for the fall prevention of old people.
Background
The patients with lower limb movement dysfunction caused by aging and various diseases are increasingly increased, the falling risks of the old people in communities and aged institutions are synchronously increased, the social cost and disease burden caused by falling are increasingly heavy, and it is very critical to timely predict the falling risks of the old people in communities and aged institutions and conduct targeted rehabilitation medical training. To construct a harmonious intelligent sanitary ecological chain, the key weight is used for rehabilitation of a basic community and a pension institution, but rehabilitation resources of the basic community and the pension institution are unevenly distributed, and homogeneous and standardized rehabilitation treatment of a tertiary hospital and a secondary hospital are difficult to obtain in the basic community and the pension institution, the basic community and the pension institution lack advanced intelligent falling-prevention assessment and training equipment, fall-prevention capability of a patient is not evaluated in real time, personalized formulated training is not performed, and accumulation and mining of rehabilitation assessment and training data information are still blank.
Disclosure of Invention
The application aims to provide an evaluation and training method and system for preventing old people from falling, a community-oriented remote training rehabilitation system is constructed, and unification of patient falling-preventing function evaluation and rehabilitation training procedures can be realized according to calculation of a falling-preventing data model of a cloud platform.
In order to achieve the above object, the present application provides a method for evaluating and training fall prevention of old people, comprising the steps of:
the cloud platform acquires a self-evaluation scale of the falling risk uploaded by the patient, and provides a pre-diagnosis suggestion according to the grading result of the scale;
guiding a patient to perform gait and balance tests on special lower limb exercise rehabilitation equipment based on the pre-diagnosis advice, wherein the lower limb exercise rehabilitation equipment acquires gait information and balance information of the patient in the test process;
the cloud platform inputs the gait information and balance information into a gait evaluation model and a balance evaluation model respectively, the step evaluation model predicts the degree of dysfunction of the gait of the patient, and the balance evaluation model predicts the degree of dysfunction of the balance of the patient;
and automatically generating an individuation training scheme applied to the lower limb exercise rehabilitation equipment according to gait and balanced dysfunction degrees, wherein the individuation training scheme comprises training subjects with different difficulties and equipment operation parameters.
Further, the gait information includes Tinetti grading data of the patient, and the balance information includes Berg grading data of the patient.
Furthermore, the gait evaluation model adopts a random forest model and a Phik correlation heat map, extracts the significance characteristics related to gait abnormality, and then selects the significance characteristics to establish a random forest model and a logistic regression model to predict the degree of dysfunction of the gait of the patient.
Further, the salient features associated with gait abnormalities include BMI, age, weight loss, average double support time, average stride width, average stance time.
Furthermore, the balance evaluation model adopts a random forest model and a Phik correlation heat map, extracts the significance characteristics related to balance abnormality, and then selects the significance characteristics to establish a random forest model and a logistic regression model to predict the degree of dysfunction of the balance of the patient.
Further, the significant features related to the balance abnormality include BMI, vestibular awareness_track length, affected side_average swing, bipedal_left and right maximum swing, vestibular awareness_maximum swing, affected side_track length, vestibular awareness_average swing speed, and healthy side_front and rear maximum swing.
Further, the degree of dysfunction of the gait includes normal, mild, moderate and severe, and the degree of dysfunction of the balance includes normal, mild, moderate and severe.
Further, the rehabilitation training scheme is set to be light, medium, heavy, medium and heavy according to the dysfunctional degree of gait and balance adjustment, the equipment parameters adjusted by the scheme comprise walking mode, pace, time, weight reduction and sitting station training times, and the training subjects set by the scheme are simple, medium and difficult.
On the other hand, the application also provides evaluation and training of the fall prevention of the old, which comprises the following steps:
the lower limb exercise rehabilitation device is used for providing lower limb rehabilitation training of multiple modes for a patient, and collecting gait data and balance data of the patient;
the cloud platform comprises a first diagnosis module, an evaluation module and a training module, wherein the first diagnosis module performs pre-evaluation on a patient through a fall risk self-evaluation table and provides pre-diagnosis advice; the evaluation module inputs the uploaded gait data and balance data into a gait evaluation model and a balance evaluation model to respectively predict the gait and balance dysfunction degree of a patient; the training module automatically generates an individuation training scheme applied to special rehabilitation equipment according to gait and balanced dysfunction degrees, wherein the individuation training scheme comprises training subjects with different difficulties and equipment operation parameters.
Further, the training mode of the lower limb rehabilitation device comprises: weight-reducing walking training, sitting training and interesting game training.
The application provides an evaluation and training method and system for preventing old people from falling, wherein a cloud platform acquires a falling risk self-evaluation scale uploaded by a patient and provides a pre-diagnosis suggestion according to a scale grading result; the patient uses special lower limb exercise rehabilitation equipment to perform rehabilitation training, and gait information and balance information of the patient are acquired in the training process; the cloud platform inputs gait information and balance information into a gait evaluation model and a balance evaluation model respectively, and an individual training scheme applied to special lower limb exercise rehabilitation equipment is automatically generated according to the gait and balance dysfunction degree; promote the patient to shunt to the community, promote the recovered ability and the level of community and endowment organization.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the application, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
Fig. 1 is a flowchart of an evaluation and training method for fall prevention of the elderly according to the present application.
Fig. 2 is a block diagram of an evaluation and training system for fall prevention of the elderly according to the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is to be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with one another without conflict.
If a similar description of "first/second" appears in the application document, the following description is added, in which the terms "first/second/third" are merely distinguishing between similar objects and not representing a particular ordering of the objects, it being understood that the "first/second/third" may be interchanged with a particular order or precedence, if allowed, so that embodiments of the application described herein may be practiced otherwise than as illustrated or described herein.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the application only and is not intended to be limiting of the application.
The application provides a method, a system and equipment for constructing a fall evaluation model based on gait abnormality, which are used for evaluating the gait ability of an elderly patient, predicting fall risk and guiding individual rehabilitation training.
Fig. 1 is a method for evaluating and training the fall prevention of the old people according to the application. As shown in fig. 1, the evaluation and training method for the fall prevention of the old people comprises the following steps:
s100, the cloud platform acquires a self-evaluation value of the fall risk uploaded by the patient, and provides a pre-diagnosis suggestion according to the evaluation result of the value;
s200, guiding a patient to perform gait and balance tests on lower limb rehabilitation equipment based on the pre-diagnosis advice, wherein the lower limb rehabilitation equipment acquires gait information and balance information of the patient in the test process;
s300, the cloud platform inputs the gait information and balance information into a gait evaluation model and a balance evaluation model respectively, the gait evaluation model predicts the degree of dysfunction of the gait of the patient, and the balance evaluation model predicts the degree of dysfunction of the balance of the patient;
s400, automatically generating an individuation training scheme applied to special rehabilitation equipment according to gait and balanced dysfunction degree, wherein the individuation training scheme comprises training subjects with different difficulties and equipment operation parameters.
In a specific embodiment, the application relates to a fall evaluation model based on gait abnormalities, which is composed of 543 cases of data (747 cases of data are totally removed, and the deletion and repetition numbers) of 4 rehabilitation institutions in an item group. The data collected by the method for the group of patients includes: height, weight, gender, age, weight loss, average stride frequency, average stride length, average stride width, average stride length time, average swing time, average standing time, average double support time, tinetti score, tinetti rating. Wherein Tinetti is rated as 1, 2 and 3 levels.
Baseline information of the data is then established, the results are first described by continuous variables for patient clinical data, and the number of outliers is removed. And (3) performing single-factor analysis of variance on the statistical data of Tinetti classification, and performing chi-square test on the discrete variables.
Specifically, the application is based on random forest, phik correlation heatmaps. Selecting salient features for modeling, wherein the features comprise: BMI, age, weight loss, average double support time, average step width, average standing time.
In the model training process, firstly, a data set of a training model is established, the data set is split into a training set and a verification set in a 7:3 mode, wherein the verification set comprises Tinetti grading sample numbers, and the Tinetti grading sample numbers comprise 1 level 19 samples, 2 level 70 samples and 3 level 73 samples. The training set is then oversampled using the SMOTE method. And constructing a random forest model by the training set, and adjusting the super parameters of the model by a random search method. The final model evaluates the degree of dysfunction in the patient's gait including normal, mild, moderate and severe.
In a specific embodiment, the application relates to a fall evaluation model data acquisition and baseline information based on balance abnormality, wherein the acquired data has Berg classification and is based on random forest and Phik correlation heat map. Selecting salient features for modeling, wherein the features comprise: BMI, vestibular awareness_trace length, affected side_average swing, bipedal_left and right maximum swing, vestibular awareness_maximum swing, affected side_trace length, vestibular awareness_average swing speed, healthy side_front and rear maximum swing.
The preferred model training process is as described above, constructing a random forest model from the training set, and adjusting the hyper-parameters of the model by a random search method. The model evaluates the degree of dysfunction in balance including normal, mild, moderate and severe.
Generating a rehabilitation training scheme automatically applied to lower limb rehabilitation equipment according to gait and balanced dysfunction degree is shown in the following table:
on the other hand, the application also provides an evaluation and training system for the fall prevention of the old, which comprises the following steps:
the lower limb rehabilitation device 102 is used for providing a patient with lower limb rehabilitation training in multiple modes, and collecting gait data and balance data of the patient;
the cloud platform 102 comprises a first diagnosis module, an evaluation module and a training module, wherein the first diagnosis module performs pre-evaluation on a patient through a fall risk self-evaluation table and provides pre-diagnosis advice; the evaluation module inputs the uploaded gait data and balance data into a gait evaluation model and a balance evaluation model to respectively predict the gait and balance dysfunction degree of a patient; the training module automatically generates an individual training scheme applied to special lower limb exercise rehabilitation equipment according to gait and balanced dysfunction degrees, and the rehabilitation training scheme comprises training subjects with different difficulties and equipment operation parameters.
Further, the training mode of the lower limb rehabilitation device comprises: weight-reducing walking training, sitting training and interesting game training.
While embodiments of the present application have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the application, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (10)
1. The evaluation and training method for the fall prevention of the old is characterized by comprising the following steps of:
the cloud platform acquires a self-evaluation scale of the falling risk uploaded by the patient, and provides a pre-diagnosis suggestion according to the grading result of the scale;
guiding a patient to use lower limb rehabilitation equipment to perform gait and balance tests based on the pre-diagnosis advice, wherein the lower limb rehabilitation equipment acquires gait information and balance information of the patient in the test process;
the cloud platform inputs the gait information and balance information into a gait evaluation model and a balance evaluation model respectively, wherein the gait evaluation model predicts the degree of dysfunction of the gait of the patient, and the balance evaluation model predicts the degree of dysfunction of the balance of the patient;
and automatically generating an individuation training scheme applied to the special rehabilitation equipment according to gait and balanced dysfunction degrees, wherein the individuation training scheme comprises training subjects with different difficulties and equipment operation parameters.
2. A method of evaluating and training an elderly fall protection according to claim 1 wherein the gait information comprises Tinetti rating data for the patient and the balance information comprises Berg rating data for the patient.
3. The method for evaluating and training the fall prevention of the elderly according to claim 2, wherein the gait evaluation model adopts a random forest model and a Phik correlation heat map, extracts the significance characteristics related to the gait, and then selects the significance characteristics to establish the random forest model and a logistic regression model to predict the degree of dysfunction of the gait of the patient.
4. A method of evaluating and training an elderly fall protection according to claim 3 wherein the salient features associated with gait anomalies include BMI, age, weight loss, average double support time, average step width, average stance time.
5. The method for evaluating and training the fall prevention of the elderly according to claim 2, wherein the balance evaluation model adopts a random forest model and a Phik correlation heat map, extracts significance characteristics related to balance, and then selects the significance characteristics to establish a random forest model and a logistic regression model to predict the degree of dysfunction of the balance of the patient.
6. The method of claim 5, wherein the balance abnormality related salient features include BMI, vestibular sensing_trace length, patient side_average swing, feet side-to-side maximum swing, vestibular sensing_maximum swing, patient side_trace length, vestibular sensing_average swing, healthy side-to-back maximum swing.
7. A method of evaluating and training protection against falls in elderly people according to claims 3 and 5 wherein the degree of dysfunction in gait comprises normal, mild, moderate and severe and the degree of dysfunction in balance comprises normal, mild, moderate and severe.
8. The method for evaluating and training the fall prevention of an elderly person according to claim 7, wherein the rehabilitation training scheme is set to be light, medium, heavy, medium and heavy according to the degree of dysfunction for adjusting gait and balance, the equipment parameters adjusted by the scheme include walking mode, pace, time, weight reduction and sitting training times, and the training subjects set by the scheme are simple, medium and difficult.
9. An evaluation and training of anti-fall for elderly people, comprising:
the special lower limb exercise rehabilitation device is used for providing a patient with lower limb exercise rehabilitation training in multiple modes, and collecting gait data and balance data of the patient;
the cloud platform comprises a first diagnosis module, an evaluation module and a training module, wherein the first diagnosis module performs pre-evaluation on a patient through a fall risk self-evaluation table and provides pre-diagnosis advice; the evaluation module inputs the uploaded gait data and balance data into a gait evaluation model and a balance evaluation model to respectively predict the gait and balance dysfunction degree of a patient; the training module automatically generates an individual training scheme applied to special lower limb exercise rehabilitation equipment according to gait and balanced dysfunction degrees, and the rehabilitation training scheme comprises training subjects with different difficulties and equipment operation parameters.
10. A method for evaluating and training an anti-fall for elderly people according to claim 1, wherein the training mode of the special lower limb exercise rehabilitation device comprises: weight-reducing walking training, sitting training and interesting game training.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310946623.7A CN116959723A (en) | 2023-07-28 | 2023-07-28 | Evaluation and training method and system for old people falling prevention |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310946623.7A CN116959723A (en) | 2023-07-28 | 2023-07-28 | Evaluation and training method and system for old people falling prevention |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116959723A true CN116959723A (en) | 2023-10-27 |
Family
ID=88452621
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310946623.7A Pending CN116959723A (en) | 2023-07-28 | 2023-07-28 | Evaluation and training method and system for old people falling prevention |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116959723A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117290686A (en) * | 2023-11-22 | 2023-12-26 | 神州医疗科技股份有限公司 | Construction method of model for predicting falling risk of patient |
-
2023
- 2023-07-28 CN CN202310946623.7A patent/CN116959723A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117290686A (en) * | 2023-11-22 | 2023-12-26 | 神州医疗科技股份有限公司 | Construction method of model for predicting falling risk of patient |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bartko | The intraclass correlation coefficient as a measure of reliability | |
| CN108780663A (en) | Digital personalized medicine platform and system | |
| CN108206058A (en) | Human body comprehensive health risk Forecasting Methodology and system | |
| CN106682412A (en) | Diabetes prediction method based on medical examination data | |
| CN109256212A (en) | Bone health assessment models construction method, device, equipment, medium and appraisal procedure | |
| CN109271969A (en) | A kind of Histopathologic Grade of Cerebral Gliomas evaluation method and its device | |
| CN116959723A (en) | Evaluation and training method and system for old people falling prevention | |
| CN110046757B (en) | Outpatient clinic volume prediction system and prediction method based on LightGBM algorithm | |
| CN106485061A (en) | A kind of life risk assessment and the method for building up of improvement system | |
| CN109920551A (en) | Autism children social action performance characteristic analysis system based on machine learning | |
| CN114652311A (en) | Fine nursing method and system based on stepped nursing intervention | |
| CN115714022A (en) | Neonatal jaundice health management system based on artificial intelligence | |
| CN106037703A (en) | Cardiorespiratory endurance indirect testing method based on intelligent exercise bicycle | |
| CN116861252A (en) | Method for constructing fall evaluation model based on balance function abnormality | |
| Dueñas et al. | Development of predictive models for the estimation of the probability of suffering fear of falling and other fall risk factors based on posturography parameters in community-dwelling older adults | |
| Sokolova et al. | A case study of muscle dysmorphia disorder diagnostics | |
| Foch et al. | Lower extremity kinematics during running and hip abductor strength in iliotibial band syndrome: A systematic review and meta-analysis | |
| JP7365747B1 (en) | Disease treatment process abnormality identification system based on hierarchical neural network | |
| CN113171082A (en) | Method and device for evaluating injury of anterior cruciate ligament | |
| CN107066816A (en) | Medical treatment guidance method, device and server based on clinical data | |
| Tang et al. | An artificial neural network algorithm for the evaluation of postoperative rehabilitation of patients | |
| Costanzo et al. | Predictive capacity of frailty phenotype toward patterns of disability identified using latent class analysis | |
| CN114202772B (en) | Reference information generation system and method based on artificial intelligence and intelligent medical treatment | |
| Zeng et al. | Detecting the presence of anterior cruciate ligament deficiency based on a double pendulum model, intrinsic time-scale decomposition (ITD) and neural networks | |
| KR20130024535A (en) | Apparatus and method for determining health state using pulse wave |
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 |