CN117133404A - Intelligent rehabilitation nursing device to thorax export syndrome - Google Patents
Intelligent rehabilitation nursing device to thorax export syndrome Download PDFInfo
- Publication number
- CN117133404A CN117133404A CN202311386910.3A CN202311386910A CN117133404A CN 117133404 A CN117133404 A CN 117133404A CN 202311386910 A CN202311386910 A CN 202311386910A CN 117133404 A CN117133404 A CN 117133404A
- Authority
- CN
- China
- Prior art keywords
- rehabilitation
- patient
- affected
- module
- outlet syndrome
- 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.)
- Granted
Links
- 230000000474 nursing effect Effects 0.000 title claims abstract description 34
- 210000000038 chest Anatomy 0.000 title claims description 20
- 208000011580 syndromic disease Diseases 0.000 title claims description 20
- 210000003205 muscle Anatomy 0.000 claims abstract description 116
- 230000000694 effects Effects 0.000 claims abstract description 45
- 238000000034 method Methods 0.000 claims abstract description 37
- 238000012544 monitoring process Methods 0.000 claims abstract description 24
- 230000003993 interaction Effects 0.000 claims abstract description 23
- 230000008569 process Effects 0.000 claims abstract description 22
- 206010048627 thoracic outlet syndrome Diseases 0.000 claims abstract description 20
- 238000011156 evaluation Methods 0.000 claims abstract description 16
- 238000011084 recovery Methods 0.000 claims description 57
- 238000004422 calculation algorithm Methods 0.000 claims description 29
- 238000012549 training Methods 0.000 claims description 24
- 230000006870 function Effects 0.000 claims description 16
- 238000003066 decision tree Methods 0.000 claims description 15
- 208000024891 symptom Diseases 0.000 claims description 11
- 238000012417 linear regression Methods 0.000 claims description 10
- 238000002560 therapeutic procedure Methods 0.000 claims description 10
- 231100000862 numbness Toxicity 0.000 claims description 7
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 6
- 230000036772 blood pressure Effects 0.000 claims description 6
- 229910052760 oxygen Inorganic materials 0.000 claims description 6
- 239000001301 oxygen Substances 0.000 claims description 6
- 239000008280 blood Substances 0.000 claims description 5
- 210000004369 blood Anatomy 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000035807 sensation Effects 0.000 claims description 5
- 238000013210 evaluation model Methods 0.000 claims description 4
- 230000008685 targeting Effects 0.000 claims description 3
- 101100478210 Schizosaccharomyces pombe (strain 972 / ATCC 24843) spo2 gene Proteins 0.000 claims description 2
- 238000011282 treatment Methods 0.000 abstract description 21
- 238000000554 physical therapy Methods 0.000 description 14
- 238000012360 testing method Methods 0.000 description 13
- 230000008676 import Effects 0.000 description 7
- 238000010801 machine learning Methods 0.000 description 7
- 208000004044 Hypesthesia Diseases 0.000 description 6
- 230000008859 change Effects 0.000 description 6
- 230000000875 corresponding effect Effects 0.000 description 6
- 208000034783 hypoesthesia Diseases 0.000 description 6
- 239000003814 drug Substances 0.000 description 5
- 230000001965 increasing effect Effects 0.000 description 5
- 230000000638 stimulation Effects 0.000 description 5
- 238000013527 convolutional neural network Methods 0.000 description 4
- 238000002059 diagnostic imaging Methods 0.000 description 4
- 229940079593 drug Drugs 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 238000012706 support-vector machine Methods 0.000 description 4
- 206010029174 Nerve compression Diseases 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 238000002567 electromyography Methods 0.000 description 3
- 230000002787 reinforcement Effects 0.000 description 3
- 208000025174 PANDAS Diseases 0.000 description 2
- 208000021155 Paediatric autoimmune neuropsychiatric disorders associated with streptococcal infection Diseases 0.000 description 2
- 240000004718 Panda Species 0.000 description 2
- 235000016496 Panda oleosa Nutrition 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000017531 blood circulation Effects 0.000 description 2
- 210000004204 blood vessel Anatomy 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 238000002651 drug therapy Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 230000033001 locomotion Effects 0.000 description 2
- 230000003183 myoelectrical effect Effects 0.000 description 2
- 210000005036 nerve Anatomy 0.000 description 2
- 230000001537 neural effect Effects 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 210000000115 thoracic cavity Anatomy 0.000 description 2
- 206010049816 Muscle tightness Diseases 0.000 description 1
- 208000012266 Needlestick injury Diseases 0.000 description 1
- 208000037273 Pathologic Processes Diseases 0.000 description 1
- 206010034568 Peripheral coldness Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 239000002260 anti-inflammatory agent Substances 0.000 description 1
- 229940124599 anti-inflammatory drug Drugs 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 210000004889 cervical nerve Anatomy 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000002591 computed tomography Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000002845 discoloration Methods 0.000 description 1
- 208000035475 disorder Diseases 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000035876 healing Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000002595 magnetic resonance imaging Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003387 muscular Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000009054 pathological process Effects 0.000 description 1
- 230000035790 physiological processes and functions Effects 0.000 description 1
- 230000006461 physiological response Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 210000002979 radial nerve Anatomy 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 238000002922 simulated annealing Methods 0.000 description 1
- 210000003270 subclavian artery Anatomy 0.000 description 1
- 210000001321 subclavian vein Anatomy 0.000 description 1
- 230000008961 swelling Effects 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
- 210000001519 tissue Anatomy 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
-
- 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
-
- 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
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
Abstract
The application relates to an intelligent rehabilitation nursing device for thoracic outlet syndrome, which comprises a rehabilitation scheme generation module, wherein the module generates a personalized rehabilitation scheme according to the positions, the number and the affected degree of affected muscles of the thoracic outlet syndrome of a patient. In addition, the nursing execution module executes corresponding nursing operation according to the generated rehabilitation scheme. The dynamic monitoring module evaluates the rehabilitation progress and effect by monitoring myoelectricity information of the affected muscles in the process of the nursing operation. And the adjusting feedback module adjusts and optimizes the rehabilitation scheme in real time according to the evaluation result of the dynamic monitoring module. And finally, the patient interaction module is used for interacting with the patient, collecting patient feedback and transmitting information. The intelligent rehabilitation nursing device provides a comprehensive solution integrating evaluation, treatment, feedback and interaction for rehabilitation treatment of patients with the thoracic outlet syndrome, thereby improving the rehabilitation nursing effect on the thoracic outlet syndrome.
Description
Technical Field
The application relates to the technical field of medicine, in particular to an intelligent rehabilitation nursing device for thoracic outlet syndrome.
Background
The thoracic outlet syndrome is a disease with complex clinical symptoms, various etiologies and difficult diagnosis and treatment, and is mainly characterized by causing compression of cervical nerves, armpit nerves, radial nerves, even subclavian arteries and veins, and causing a series of symptoms such as numbness of arms, pain, weakness, even finger swelling and discoloration, and the like, due to abnormal structures of thoracic outlet (including shoulder bones, first ribs and rear sides of cervical vertebrae), muscular tension, poor posture, and the like. Treatment of the thoracic outlet syndrome has remained a medical challenge to date.
Because the symptoms of the chest outlet syndrome are complex, the conventional treatment modes such as physical treatment, drug treatment, rehabilitation training and the like often cannot solve the problems well. Therefore, the intelligent rehabilitation nursing device which can comprehensively know the illness state of a patient, generate a personalized rehabilitation scheme according to the specific condition of the patient, dynamically monitor the rehabilitation process in real time and adjust and optimize according to the rehabilitation effect is developed, so that the nursing effect on the thoracic outlet syndrome is improved, and the intelligent rehabilitation nursing device is an important direction of current research.
Disclosure of Invention
The application provides an intelligent rehabilitation nursing device for thoracic outlet syndrome, which has nursing effect on the thoracic outlet syndrome.
The application provides an intelligent rehabilitation nursing device for thoracic outlet syndrome, which comprises: the rehabilitation scheme generation module is used for generating a personalized rehabilitation scheme according to the positions, the number and the affected degree of affected muscles of the patient chest outlet syndrome;
the nursing execution module is used for executing corresponding nursing operation according to the personalized rehabilitation scheme;
the dynamic monitoring module is used for monitoring myoelectricity information of affected muscles in the nursing operation process and evaluating rehabilitation progress and effect;
the adjusting feedback module is used for adjusting and optimizing the rehabilitation scheme in real time according to the evaluation result of the dynamic monitoring module;
and the patient interaction module is used for interacting with a patient.
Still further, the rehabilitation regimen generation module includes a goal determination unit and a regimen generation unit; the target determination unit is used for determining overall targets of rehabilitation therapy, including recovery strength of affected muscles, recovery time period and recovery strength of affected degrees; the scheme generating unit is used for generating a personalized rehabilitation scheme according to the overall target.
Still further, the target determining unit further includes:
a data input subunit for receiving input data regarding the location, number and extent of affected muscles;
a decision tree model for assessing patient severity by analyzing the location and number of affected muscles;
a linear regression model for combining the extent of affected muscles to determine the recovery time period.
Still further, the target determination unit further includes a recovery intensity setting subunit for setting the recovery intensity of each affected muscle based on the degree of involvement of the affected muscle and information of the age, physical condition, recovery ability, and the like of the patient.
Still further, the target determining unit further includes a rehabilitation intensity setting subunit, the subunit searches for an optimal rehabilitation intensity by using a gradient descent algorithm, and the gradient descent algorithm uses an objective function f (x) as follows:
f(x) = Σ wi * (di - xi)2
where xi is the rehabilitation intensity of the ith affected muscle, di is the extent of its involvement, wi is a weight indicating the effect of the ith muscle on the outcome of the rehabilitation regimen.
Still further, the dynamic monitoring module evaluates the rehabilitation effect using an evaluation model, which is calculated in part using the following formula:
e_total=Σ (α 1_i ×a_i+α 2_i ×f_i+α 3_i ×e_i+α4×hr+α5×bp+α6×spo2), where e_total is a total evaluation value of rehabilitation effect, α 1_i to α6 are weights of respective parameters, a_i is the amplitude of the electromyographic signal of the i-th block affected muscle, f_i is the main frequency of the electromyographic signal of the i-th block affected muscle, e_i is the entropy of the electromyographic signal of the i-th block affected muscle, HR is heart rate, BP is blood pressure, spO2 is blood oxygen saturation.
Further, the adjustment feedback module specifically includes the following steps according to the evaluation result of the dynamic monitoring module:
(a) Judging whether the total evaluation value E_total is smaller than a preset threshold value E_total_threshold or whether the entropy E_i of any electromyographic signals is larger than the preset threshold value E_i_threshold;
(b) If any one of the conditions in the step (a) is satisfied, calculating an adjustment value for the intensity or frequency of the rehabilitation training, wherein the specific formula is as follows: Δs=β1 (e_total-e_total_old) +β2 (e_i-e_i_old), where Δs is the adjustment value of the intensity or frequency of the rehabilitation training, e_total_old and e_i_old are the values of e_total and e_i at the time of the last calculation, β1 and β2 are weights.
Still further, the settings of E_total_threshold and E_i_threshold are based on the patient's specific situation and the physician's experience.
Still further, the patient interaction module includes a user interface that allows the patient to enter own symptoms and sensations, including information on pain location, pain level, numbness or frequency of tingling.
Still further, the patient interaction module provides real-time feedback to the patient through a feedback interface, including rehabilitation progress and outcome assessment results. Furthermore, the method also comprises the steps of collecting personal information of the tested individual, wherein the personal information comprises age, gender, weight, height, history of diseases and the like, and inputting the personal information and other characteristic data into a model, so that the prediction accuracy is improved.
The technical scheme provided by the application is different from other schemes in the prior art, and can generate a personalized rehabilitation scheme according to the positions, the number and the affected degree of affected muscles of the patient chest outlet syndrome. And then, by comparing myoelectricity information of affected muscles in the nursing operation process, the rehabilitation progress and effect are estimated, and the rehabilitation scheme is adjusted and optimized in real time according to the estimation result.
The technical scheme provided by the application has the following beneficial technical effects:
(1) Providing a more personalized rehabilitation regimen: by analyzing the patient's specific symptoms and the information of the affected muscles, a personalized rehabilitation regimen specific to the patient is generated.
(2) Dynamic optimization rehabilitation scheme: through real-time monitoring and evaluation rehabilitation process, can carry out real-time scheme adjustment according to the rehabilitation effect for rehabilitation scheme is in the state that is most suitable for the patient all the time.
(3) Enhancing patient experience: through the patient interaction module, the patient can more intuitively know own illness state and rehabilitation progress, and can provide precious feedback at the same time, so that the treatment process is more in line with the actual demands of the patient.
Drawings
Fig. 1 is a schematic diagram of an intelligent rehabilitation and nursing device for thoracic outlet syndrome according to a first embodiment of the present application.
Detailed Description
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. The present application may be embodied in many other forms than those herein described, and those skilled in the art will readily appreciate that the present application may be similarly embodied without departing from the spirit or essential characteristics thereof, and therefore the present application is not limited to the specific embodiments disclosed below.
The first embodiment of the application provides an intelligent rehabilitation and nursing device for thoracic outlet syndrome. Referring to fig. 1, a schematic diagram of a first embodiment of the present application is shown. The following provides a detailed description of an intelligent rehabilitation and nursing device for thoracic outlet syndrome according to a first embodiment of the present application with reference to fig. 1.
The intelligent rehabilitation nursing device for the chest outlet syndrome comprises a rehabilitation scheme generation module 101, a nursing execution module 102, a dynamic monitoring module 103, an adjustment feedback module 104 and a patient interaction module.
The rehabilitation scheme generating module 101 is configured to generate a personalized rehabilitation scheme according to the position, the number and the affected degree of the affected muscles of the chest outlet syndrome of the patient.
The location, number, and extent of the affected muscles can be obtained by combining conventional medical imaging techniques with advanced image analysis algorithms. The following is a detailed procedure.
Step S1001, medical imaging acquisition: at this step, the patient is fully scanned using advanced medical imaging techniques (e.g., MRI or CT scanning) to obtain detailed images of the thoracic outlet region. These images should be able to clearly show the location, shape and size of various biological tissues including muscles, nerves, blood vessels.
Step S1002, image preprocessing: since medical imaging typically generates large amounts of data, some preprocessing operations are required to simplify the analysis process. This may include image enhancement (to improve the visibility of the image), image segmentation (to separate the region of interest from the background), noise reduction, and the like.
Step S1003, affected muscle identification: in this step, advanced image analysis algorithms such as deep learning are used to identify affected muscles in the image. In particular, convolutional neural network (CNN, convolutional Neural Networks) algorithms may be used that perform well in image recognition tasks. CNN determines which areas in an image are affected muscles by learning the features of a large number of marked images (i.e., images of which parts are known to be affected muscles) and then applying to the new unmarked images.
Step S1004, calculating the affected degree: after the location and number of affected muscles are determined, it is also necessary to determine the extent of the affected muscles. This can be achieved by analysing the properties of the muscle in the image, such as brightness, colour, shape, etc., as these properties typically change as the muscle is damaged. To this end, an algorithm may be designed to quantify these changes and to evaluate the degree of involvement of the muscle. The algorithm comprises the following steps:
step S1004-1, image preprocessing: to obtain a more accurate degree of involvement, the acquired image is first preprocessed. Including denoising, normalization, contrast enhancement, etc. This may be achieved by a series of image processing techniques such as median filtering, histogram equalization, etc.
Step S1004-2, feature extraction: after the image preprocessing is completed, the next step is to extract key features in the image. These characteristics may include the brightness, color, shape, etc. of the muscle. Since these properties generally change as the muscle is damaged, they can be an important indicator for assessing the degree of muscle involvement.
In a specific implementation, the brightness can be obtained by calculating the average value of the pixel values; the color may then be analyzed by performing an analysis in the HSV color space, such as calculating an average hue value for the muscle region; the shape may be represented by calculating the edge contour of the muscle region and then using geometric parameters (e.g., area, circumference, direction, etc.).
Step S1004-3, an estimation model is established: after the extraction of the key features, the degree of involvement of the muscle is then estimated from these features. This may be achieved by some machine learning method, such as a Support Vector Machine (SVM), random Forest (Random Forest), or deep learning method.
For example, an SVM model may be constructed, the input features of which are parameters such as brightness, color, shape, etc. extracted in the previous step, and the output result is the degree of involvement of the muscle. In this process, a labeled training dataset may be required for model training.
Therefore, through the steps, the specific information such as the positions, the number and the affected degree of the affected muscles of the patient chest outlet syndrome can be obtained directly through the technical means, so that basic data and basis are provided for subsequent treatment and rehabilitation.
In the rehabilitation regimen generation module 101, the present embodiment provides an adaptive chest outlet syndrome rehabilitation (ATOSRA, adaptive Thoracic Outlet Syndrome Rehabilitation Algorithm) algorithm using machine learning and artificial intelligence techniques. The specific steps and implementation of the ATOSRA algorithm are as follows:
step S2001: based on the obtained specific information of the location, number and extent of involvement of the involved muscles, the atora algorithm will first determine the overall goal of the rehabilitation therapy, including the strength of recovery for the involved muscles, the duration of the rehabilitation time, and the strength of recovery for the extent of involvement. First, concepts such as the recovery strength of the affected muscle and the recovery strength for the affected degree will be explained. This step may be implemented in the targeting unit of the rehabilitation scenario generation module 101.
The recovery strength of the affected muscles refers to how much therapeutic force needs to be applied to each affected muscle in order to achieve the goal of rehabilitation. This includes the frequency of treatment (e.g., several treatments per week), the intensity of treatment (e.g., how much force of massage or physical treatment is required per treatment), and the duration of treatment (how long each treatment is required), etc.
The rehabilitation strength refers to the strength or pressure applied to the muscle by rehabilitation therapy. For example, if the patient is undergoing physical therapy, the strength of recovery may refer to the force applied by the therapist or the machine set force. Alternatively still, if the patient is undergoing electrical stimulation therapy, the intensity of recovery may refer to the intensity of the electrical current. The rehabilitation intensity may also be an adjustable parameter by which, for example, the instrument may automatically change the force or pressure applied to the muscle to achieve an optimal rehabilitation effect.
In the ATOSRA algorithm, determining a rehabilitation goal is a key step involving a number of steps:
step S2001-1, data input: the entered data includes the location, number, degree of involvement, etc. of the involved muscles. This step may be performed by the data input subunit.
Step S2001-2, determining an overall rehabilitation target: the ATOSRA algorithm sets the overall goal of rehabilitation therapy by innovative methods. First, the algorithm evaluates the severity of the patient's condition by analyzing the location and number of affected muscles. This step may be implemented using a machine learning method such as a decision tree or support vector machine. The algorithm then uses the degree of involvement as a weight, in combination with previous assessment results, to set a recovery time period. Algorithms that may be used in this process include linear regression or neural networks, etc.
The present embodiment next describes how to construct a decision tree model and a linear regression model with two specific examples, and indicates the inputs and outputs of the two models.
(1) Decision tree model
The following training data sets are assumed:
wherein the input characteristics include "number of affected muscles", "location of affected muscles" and "degree of affected", and the output is "severity of illness".
The embodiment can train a decision tree model through the data. The model construction process involves many mathematical and statistical details such as information gain, base index, etc. In short, the model will find the best feature classification point based on the training data to maximize the discrimination between different output classes. In this example, the model may determine that the severity of the condition is high when the number of affected muscles is greater than 1 and the extent of the affected muscles is greater than 60%; otherwise, the severity of the condition is medium or low.
How to implement the decision tree model will be briefly described below using the Python language and the common machine learning library scikit-learn as an example.
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
# creation dataset
data = {
'Muscle Count': [2, 1, 3, 1],
'Muscle Location': ['left', 'right', 'both', 'left'],
'Affected Degree': [80, 50, 90, 30],
'Severity': ['high', 'medium', 'high', 'low']
}
df = pd.DataFrame(data)
# convert character string to number so that machine learning model can handle
df['Muscle Location'] = df['Muscle Location'].map({'left': 1, 'right': 2, 'both': 3})
df['Severity']=df['Severity'].map({'low': 1, 'medium': 2, 'high': 3})
# divide the dataset into training and testing sets
X = df.drop('Severity', axis=1)
y = df['Severity']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
Training decision tree model
model = DecisionTreeClassifier()
model.fit(X_train, y_train)
# test model
print(model.score(X_test, y_test))
(2) Linear regression model
The following training data sets are assumed:
wherein the input characteristics include "severity of illness" and "severity of involvement", and the output is "recovery time period".
A linear regression model can be trained from the above data. The model construction process involves many mathematical and statistical details, such as least squares, gradient descent, etc. In short, the model will find the best linear relationship based on the training data to minimize the gap between the predicted and actual values. In this example, the model may derive the following relationship: recovery time period = 2 x severity of illness + 0.05 x severity of involvement + 1.
In the following, a brief description will be given of how to implement a linear regression model, using the Python language and the usual machine learning library scikit-learn as an example.
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
# creation dataset
data = {
'Severity': [3, 2, 3, 1],
'Affected Degree': [80, 50, 90, 30],
'Recovery Time': [9, 6, 12, 4]
}
df = pd.DataFrame(data)
# divide the dataset into training and testing sets
X = df.drop('Recovery Time', axis=1)
y = df['Recovery Time']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
Training linear regression model
model = LinearRegression()
model.fit(X_train, y_train)
# test model
print(model.score(X_test, y_test))
Step S2001-3, setting the recovery intensity of the affected muscle: the ATOSRA algorithm takes an innovative strategy in setting the intensity of recovery of the affected muscle. For each affected muscle, the algorithm first sets an initial recovery strength based on its extent of involvement. And then, according to the information of the age, physical condition, rehabilitation capability and the like of the patient, the rehabilitation strength is refined and adjusted. This process may use advanced artificial intelligence techniques such as rule-based systems, or deep reinforcement learning. This step may be performed by the restoration strength setting subunit in the target determination unit.
The following is a specific example for this step:
first, it is necessary to define the strength of recovery of an affected muscle. This may be a value in the range of 1 to 10, representing from the lightest recovery strength (1) to the strongest recovery strength (10).
Then, a rule-based system, or a deep reinforcement learning model, is created for calculating the initial recovery strength of each affected muscle based on the information of the affected muscle's affected degree, the patient's age, physical condition, recovery ability, etc.
For example, a simple rule system may be used as follows:
if the degree of involvement is less than 40%, the recovery strength is 3;
if the degree of involvement is between 40% and 70%, the recovery strength is 6;
if the degree of involvement is greater than 70%, the recovery strength is 9.
After the initial recovery strength is determined, fine adjustments may be made based on the patient's personal information. For example, if the patient is older or in poor physical condition, the recovery strength may be reduced appropriately; conversely, if the patient is of a lesser age or in good physical condition, the recovery strength may be suitably increased.
For example, the following rules may be created:
if the patient is older than 60 years old, the recovery intensity is reduced by 2;
if the physical condition (such as heart rate, blood pressure and other indexes) of the patient is lower than the normal range, the recovery strength is reduced by 1;
if the patient has strong rehabilitation ability (good exercise habit is present), the recovery strength is increased by 1.
In this way, the recovery strength of each affected muscle is obtained.
Note that the above rules and values are examples only. In actual use, these rules and values need to be set according to specific medical knowledge and practice experience, and may require extensive testing and adjustment. If a deep reinforcement learning model is used, a significant amount of training data and computational resources are also required.
In addition, more complex models, such as deep neural networks, or other advanced artificial intelligence techniques, may be used to more accurately set the recovery strength. This would require more specialized knowledge and technology but may give better results.
Step S2001-4, setting a rehabilitation strength for the affected degree: the atora algorithm will also set an appropriate rehabilitation strength for each affected muscle affected. The specific setting mode is that for the muscle with higher affected degree, the set rehabilitation strength is larger, and conversely, smaller. This process may be accomplished by some optimization algorithm, such as gradient descent or simulated annealing, etc. This step may be performed by a rehabilitation intensity setting subunit in the targeting unit.
The specific implementation may be as follows:
first, an initial rehabilitation strength is set for each affected muscle. This may be done using the methods described above, but other methods may be used, such as setting the initial rehabilitation intensity of all muscles to medium intensity (e.g. 5).
Next, an objective function needs to be defined, representing the effect of the rehabilitation regimen. The input to the objective function is the intensity of rehabilitation for each affected muscle and the output is the expected effect of the rehabilitation regimen. This function may be based on medical knowledge and experience, or may be learned from a large amount of historical data.
For example, the objective function may be in the form of:
f(x) = Σ wi * (di - xi)2
where xi is the rehabilitation intensity of the ith affected muscle, di is the extent of its involvement, wi is a weight indicating the effect of the ith muscle on the outcome of the rehabilitation regimen. This function indicates that the more the strength of a muscle is different from its affected level, the less effective the rehabilitation regimen will be.
An optimization algorithm, such as a gradient descent algorithm, may then be used to find the optimal rehabilitation strength. The specific steps may be as follows:
(1) The gradient of the objective function is calculated using a gradient descent algorithm. In this embodiment, the gradient is the partial derivative of the rehabilitation intensity with respect to each muscle.
(2) The rehabilitation intensity of each muscle is adjusted according to the direction of the gradient. In this embodiment, if the partial derivative of a certain muscle is positive, it is indicated that increasing the rehabilitation strength can improve the effect of the rehabilitation scheme, so that the rehabilitation strength can be increased; and vice versa.
(3) Repeating the above steps until the optimal rehabilitation strength is found.
It should be noted that the above objective function and gradient descent algorithm are just one possible implementation. In actual use, adjustments may be required based on specific medical knowledge and practical experience. Moreover, this process can be complex and time consuming, and may require specialized knowledge and technical support.
Step S2002: the atora algorithm generates a personalized rehabilitation regimen based on the overall goals of rehabilitation therapy. The rehabilitation goals, including the strength of recovery of the affected muscle, the duration of recovery time, strength of recovery for the extent of the affected, etc., may be used as inputs to generate a personalized rehabilitation regimen using a decision tree algorithm. This step may be performed by the protocol generation unit in the rehabilitation protocol generation module 101.
The decision tree model will be trained using these input features to generate a series of decision rules to determine the optimal rehabilitation strategy. At each decision node, the model judges a feature and splits the rehabilitation process into different subtasks according to the judging result. For example, if the "recovery intensity" is low and the "recovery time period" is long, the decision tree model may select a recovery strategy that includes "low intensity physiotherapy" and "transcutaneous electrical stimulation (TENS)". Conversely, if the "recovery intensity" is higher and the "recovery time period" is shorter, the model may choose a recovery strategy that includes "high intensity physiotherapy" and "drug therapy
In the following, it will be briefly described how to implement the decision tree, using the Python language and the usual machine learning library scikit-learn as an example.
from sklearn import tree
Data on # rehabilitation goals and rehabilitation strategies
X= [ [..], [ (..] ],.], for example [ [0.8, 6, 0.7], [0.6, 4, 0.6], ] a # rehabilitation goal
Y= [..] # rehabilitation strategy, e.g [ "high intensity physical therapy+drug therapy", "medium intensity physical therapy", "low intensity physical therapy", "high intensity physical therapy+transcutaneous electrical stimulation",.]
# build decision tree model and train
clf = tree.DecisionTreeClassifier()
clf = clf.fit(X, Y)
Prediction of new rehabilitation
new_case= [. The.+ -. New rehabilitation situation ] # e.g. [0.7, 5, 0.6]
prediction = clf.predict([new_case])
print("Predicted rehabilitation strategy:", prediction)
Once the decision tree outputs the rehabilitation strategy, a function can be designed to generate the corresponding rehabilitation scheme. This function may take as input a rehabilitation strategy and then output a detailed rehabilitation regimen, which may include specific treatment items, frequencies, intensities, durations, etc. The following is an example of one such function:
def generate_rehab_plan(rehab_strategy):
the rehabilitating program of rehabilitating_plan = { } # is a dictionary and comprises various treatment items and specific contents thereof
Resolving recovery strategy to generate recovery scheme
if "high intensity physiotherapy" in rehab_strategy:
rehab_plan [ "physical therapy" ] = { "intensity": "high", "frequency": "5 times per week", "duration": "1 hour each time" }
if "medium intensity physiotherapy" in rehab_strategy:
rehab_plan [ "physical therapy" ] = { "intensity": "medium", "frequency": "3 times per week", "duration": "45 minutes each time" }
if "low intensity physiotherapy" in rehab_strategy:
rehab_plan [ "physical therapy" ] = { "intensity": "low", "frequency": "2 times per week", "duration": "30 minutes each time" }
if "transcutaneous electrical stimulation" in rehab_strategy:
rehab_plan [ "transcutaneous electrical stimulation" ] = { "frequency": 3 times per week "," duration ": 30 minutes each time" }
if "medication" in rehab_strategy:
rehab_plan [ "drug treatment" ] = { "drug": "anti-inflammatory drug", "dose": once daily "}
return rehab_plan
Generating a rehabilitation regimen using a decision tree predicted rehabilitation strategy
predicted_strategy = clf.predict([new_case])
rehab_plan = generate_rehab_plan(predicted_strategy[0])
The care execution module 102 is configured to execute a corresponding care operation according to the personalized rehabilitation scheme.
The care execution module 102 is controlled by a program having a function of parsing and executing the personalized rehabilitation regimen. The nursing execution module can control the working mode and the working parameters of the nursing instrument according to the analyzed scheme content. For example, when a particular therapy is recommended by the rehabilitation program, the care execution module may control the therapy device to operate according to parameters such as recommended therapy mode, frequency, intensity, etc.
The dynamic monitoring module 103 is used for evaluating the rehabilitation progress and effect by comparing myoelectricity information of the affected muscles in the nursing operation process.
The dynamic monitoring module 103 is a very important part for assessing the progress and effect of rehabilitation in real time. The operation of this module is based mainly on Electromyography (EMG) information of the affected muscles. Specifically, it will compare the myoelectricity changes of the affected muscles before and after the start of the care session, and then use this information to assess the progress and effect of rehabilitation.
The method comprises the following specific steps:
first, the dynamic monitoring module 103 will perform Electromyographic (EMG) acquisitions for each affected muscle. EMG is a technique for recording the electrical activity of muscles that captures the electrical signals produced by the muscles as they contract and relax.
For each affected muscle, the dynamic monitoring module 103 will calculate several key parameters of its electromyographic signals, including amplitude (a_i), dominant frequency (f_i) and entropy (e_i). The amplitude reflects the intensity of the muscle activity, the dominant frequency reflects the velocity of the muscle activity, and the entropy is a measure of the complexity of the signal, which can reflect the stability and uniformity of the muscle activity.
The calculation method of the entropy (E_i) is to use an algorithm such as shannon entropy or sample entropy, and the specific calculation mode comprises the following steps:
first, the myoelectric signal is normalized to be between 0 and 1.
The frequency at which each possible signal value appears in the overall signal is then calculated.
Finally, the entropy is calculated using the following formula:
E_i = -Σ(p * log(p))
where p is the frequency of each signal value, log is a logarithmic function, and Σ represents the summation.
After calculating these parameters, the dynamic monitoring module 103 inputs this information into an evaluation model, which is of the form:
E_total = Σ (α1_i * A_i + α2_i * F_i + α3_i * E_i + α4 * HR + α5 * BP + α6 * SpO2)
the parameters involved in the above formulas are described in detail below.
E_total: this is an overall evaluation of the rehabilitation effect. It is obtained by multiplying the other parameters by the corresponding weights and summing.
α 1_i, α 2_i, α 3_i, α4, α5 and α6: these are weights for the individual parameters. They can be adjusted according to the specific condition of the patient and the experience of the doctor. The weight may reflect the extent to which the parameter affects the assessment of rehabilitation effect. For example, if α 1_i is greater than α 2_i, the amplitude A_i of the electromyographic signal has a greater effect on the healing effect than the primary frequency F_i.
A_i: this is the amplitude of the electromyographic signal of the ith affected muscle. It may reflect the intensity of muscle activity.
F_i: this is the dominant frequency of the electromyographic signals of the ith affected muscle. It may reflect the rate or frequency of muscle electrical activity.
E_i: this is the entropy of the electromyographic signals of the affected muscle of the ith block. Entropy is an indicator of the complexity of a measured signal, which may reflect the stability or predictability of muscle activity.
HR: this is the heart rate. The heart rate changes can reflect the physiological response and pressure level of the body, and have a certain influence on the assessment of rehabilitation effect.
BP: this is blood pressure. The change of blood pressure can reflect the physiological state of the body, and has a certain influence on the assessment of rehabilitation effect.
SpO2: this is the blood oxygen saturation. The blood oxygen saturation can reflect the condition of oxygen supply in the body and has a certain influence on the assessment of rehabilitation effect.
Finally, the dynamic monitoring module 103 analyzes the e_total, and if the e_total is continuously increased in a period of time, the rehabilitation process can be considered to be smooth, and the rehabilitation effect is good; if E_total continues to drop over a period of time, then it may be necessary to adjust the rehabilitation regimen.
In general, dynamic monitoring module 103 may effectively evaluate rehabilitation progress and effect by comparing the myoelectricity of the affected muscles during the care operation.
And the adjustment feedback module 104 is used for adjusting and optimizing the rehabilitation scheme in real time according to the evaluation result of the dynamic monitoring module. The module is a key link for ensuring that the personalized rehabilitation scheme can be adjusted in real time along with the change of the rehabilitation process so as to achieve the optimal rehabilitation effect.
Firstly, the adjustment feedback module receives data input of the dynamic monitoring module, including myoelectricity information of affected muscles, data such as heart rate, blood pressure, blood oxygen saturation and the like, and total evaluation value E_total of rehabilitation effect and the like.
Then, the adjustment feedback module applies the determined formulas to process the data to generate an adjustment suggestion for the rehabilitation regimen. For example, if the entropy of the myoelectrical information of a certain affected muscle group increases, indicating that the activity of this muscle group is more complex and unstable, it may be desirable to increase the intensity or frequency of rehabilitation training for this muscle group.
The formula for adjusting the feedback module may include, but is not limited to, the following two parts:
one is to judge whether the rehabilitation scheme needs to be adjusted according to the total evaluation value E_total and the myoelectricity information entropy E_i of each affected muscle group. If E_total is less than a preset threshold, or some E_i is greater than a preset threshold, then it may be necessary to adjust the rehabilitation regimen. This process can be expressed by the following formula:
adjustment flag=1 (when e_total < e_total_threshold or any e_i > e_i_threshold)
Wherein, E_total_threshold and E_i_threshold are preset thresholds, and are set according to the experience of doctors and the specific condition of patients.
And the other is to calculate the adjustment value of the intensity or frequency of the rehabilitation training according to the change conditions of E_total and E_i. This process can be expressed by the following formula:
ΔS = β1 * (E_total - E_total_old) + β2 * (E_i - E_i_old)
where Δs is an adjustment value of intensity or frequency of rehabilitation training, e_total_old and e_i_old are values of e_total and e_i at the time of last calculation, and β1 and β2 are weights, which can be set according to experience of doctor and specific condition of patient.
Through the two formulas, the rehabilitation scheme can be adjusted and optimized in real time.
In addition, the adjustment feedback module also considers the individuation characteristic of the chest outlet syndrome. For example, depending on the location, number, and extent of affected muscles of the patient, adjusting the feedback module may generate a more personalized rehabilitation regimen. For example, if the neck and shoulder muscles of the patient are simultaneously affected, the adjustment feedback module may suggest a number of rehabilitation training methods that are capable of simultaneously training the neck and shoulder muscles. If the patient's shoulder and arm muscles are involved at the same time, the adjustment feedback module may recommend a rehabilitation regimen for both the shoulder and arm, such as physical therapy in combination with appropriate elastic band training. If the degree of numbness of the fingers of the patient is high, the adjustment feedback module can recommend adding more fine motion training of the fingers, such as pinching exercise with fine objects, and improving the feeling and the movement ability of the fingers. If the patient has severe nerve compression and hand function is limited, the adjustment feedback module may recommend neural sliding technology to help improve neural activity and alleviate hand symptoms. For patients with higher pain and stiffness, adjusting the feedback module may recommend that the patient perform more heat and light muscle stretching exercises to relieve muscle tension and reduce pain. If the patient's work or lifestyle results in frequent specific actions that may aggravate the condition, the adjustment feedback module recommends changing or adjusting those actions that may aggravate the condition to reduce the risk of recurrence.
Finally, the adjustment feedback module feeds back the adjustment suggestions to the rehabilitation scheme generation module and the nursing execution module, guides the rehabilitation scheme generation module and the nursing execution module to generate new rehabilitation schemes, and executes corresponding nursing operation.
By means of the mode, the feedback module can be adjusted to ensure real-time optimization and individuation of a rehabilitation scheme, the rehabilitation effect is improved, and the rehabilitation requirement of patients with the chest outlet syndrome is better met.
A patient interaction module 105 for interacting with a patient. The module is provided with a friendly man-machine interaction interface, the rehabilitation progress is fed back in real time, parameters are adjusted and the like, and a patient can acquire the treatment progress through the module, ask questions or give feedback.
The patient interaction module 105 is an important part of the intelligent rehabilitation and care device for the chest outlet syndrome, which is mainly responsible for effective information exchange and feedback with the patient.
The specific symptoms and experiences of each patient may vary during the course of treatment of the chest outlet syndrome. The design of this module will therefore be specifically tailored to the nature of the disorder. For example, it provides an intuitive user interface that allows the patient to easily input his or her own symptoms and sensations, including information on pain location, pain level, numbness or tingling. This information will be used to update the rehabilitation regimen and assess the rehabilitation effect.
In addition, the patient interaction module may also provide real-time feedback to the patient through a feedback interface. The rehabilitation progress and effect evaluation result of the patient can be displayed, so that the patient can be helped to know the rehabilitation condition of the patient. At the same time, when the adjustment feedback module makes new rehabilitation training advice, the patient interaction module will also present these advice to the patient in an easily understood manner.
To enhance the user experience, the patient interaction module may also provide multi-language support, voice recognition, text-to-speech conversion, etc. to accommodate the needs and preferences of different patients.
Still further, the patient interaction module 105 also provides an interface for displaying shoulder neck and arm detail models. This model needs to have rotation, zoom, etc. functions to facilitate patient viewing and manipulation from multiple angles. Meanwhile, the model needs to contain structures of muscles, nerves, blood vessels and the like, and the structures can be distinguished by means of colors, textures and the like. In the design of the User Interface (UI), a clickable marking tool is also included to allow the patient to mark the location of pain or numbness directly on the model.
The patient interaction module 105 also provides a nerve compression sensing feedback interface that includes a plurality of preset options, each of which represents a particular nerve compression sensation (e.g., needle stick, numbness, heat, cold, etc.). Options may be graphically represented (e.g., with ice cubes representing "cold feel" and flames representing "hot feel") to increase user friendliness. The patient may click on one or more options to describe their sensation.
The patient interaction module 105 also provides a blood flow condition input interface in which some preset options may be provided, such as "cold hands", "purple arms", etc. At the same time, a text entry box may be provided to allow the patient to specify their blood flow status.
The patient interaction module 105 also provides a muscle group usage feedback interface in which some common daily activities (e.g., lifting, twisting caps, etc.) can be listed, and the patient can hook beside the corresponding activity, indicating that the activity is being performed with difficulty or pain. At the same time, a text entry box should be provided for the patient to enter other non-preset activities.
The patient interaction module 105 also provides a specialized educational information interface that may include a series of images and animations that visually present information about the etiology, pathological processes, symptoms of the chest outlet syndrome, etc. Meanwhile, the utility model also contains some educational contents, such as correct sitting posture, sleeping posture, breathing mode and the like, which help patients prevent symptoms from occurring or aggravating in daily life.
In general, the patient interaction module is a highly personalized and user friendly interaction system aimed at improving the patient's rehabilitation effect and satisfaction.
While the application has been described in terms of preferred embodiments, it is not intended to be limiting, but rather, it will be apparent to those skilled in the art that various changes and modifications can be made herein without departing from the spirit and scope of the application as defined by the appended claims.
Claims (10)
1. An intelligent rehabilitation and care device for thoracic outlet syndrome, comprising:
the rehabilitation scheme generation module is used for generating a personalized rehabilitation scheme according to the positions, the number and the affected degree of affected muscles of the patient chest outlet syndrome;
the nursing execution module is used for executing corresponding nursing operation according to the personalized rehabilitation scheme;
the dynamic monitoring module is used for evaluating the rehabilitation progress and effect by monitoring myoelectricity information of affected muscles in the nursing operation process;
the adjusting feedback module is used for adjusting and optimizing the rehabilitation scheme in real time according to the evaluation result of the dynamic monitoring module;
and the patient interaction module is used for interacting with a patient.
2. The intelligent rehabilitation and care device for the chest outlet syndrome according to claim 1, wherein the rehabilitation regimen generation module comprises a goal determination unit and a regimen generation unit;
the target determination unit is used for determining overall targets of rehabilitation therapy, including recovery strength of affected muscles, recovery time period and recovery strength of affected degrees;
the scheme generating unit is used for generating a personalized rehabilitation scheme according to the overall target.
3. An intelligent rehabilitation and care device for thoracic outlet syndrome according to claim 2, wherein the targeting unit further comprises:
a data input subunit for receiving input data regarding the location, number and extent of affected muscles;
a decision tree model for assessing patient severity by analyzing the location and number of affected muscles;
a linear regression model for combining the extent of involvement of the involved muscles to determine a recovery time period.
4. An intelligent rehabilitation and care device for chest outlet syndrome according to claim 3, wherein the target determination unit further comprises a recovery strength setting subunit for setting the recovery strength of each affected muscle according to the affected degree of the affected muscle and the age, physical condition, and recovery ability information of the patient.
5. An intelligent rehabilitation and care device for chest outlet syndrome according to claim 3, wherein the target determination unit further comprises a rehabilitation strength setting subunit, the rehabilitation strength setting subunit uses a gradient descent algorithm to find an optimal rehabilitation strength, and the gradient descent algorithm uses an objective function f (x) as follows:
f(x) = Σ wi * (di - xi)2
where xi is the rehabilitation intensity of the ith affected muscle, di is the extent of its involvement, wi is a weight indicating the effect of the ith muscle on the outcome of the rehabilitation regimen.
6. The intelligent rehabilitation and care device for the thoracic outlet syndrome according to claim 1, wherein the dynamic monitoring module evaluates the rehabilitation effect by using an evaluation model, and the evaluation model is calculated by the following formula:
e_total=Σ (α 1_i ×a_i+α 2_i ×f_i+α 3_i ×e_i+α4×hr+α5×bp+α6×spo2), where e_total is a total evaluation value of rehabilitation effect, α 1_i to α6 are weights of respective parameters, a_i is the amplitude of the electromyographic signal of the i-th block affected muscle, f_i is the main frequency of the electromyographic signal of the i-th block affected muscle, e_i is the entropy of the electromyographic signal of the i-th block affected muscle, HR is heart rate, BP is blood pressure, spO2 is blood oxygen saturation.
7. The intelligent rehabilitation and nursing device for the thoracic outlet syndrome according to claim 6, wherein the adjustment feedback module adjusts and optimizes the rehabilitation scheme in real time according to the evaluation result of the dynamic monitoring module, and specifically comprises the following steps:
(a) Judging whether the total evaluation value E_total is smaller than a preset threshold value E_total_threshold or whether the entropy E_i of any electromyographic signals is larger than the preset threshold value E_i_threshold;
(b) If any one of the conditions in the step (a) is satisfied, calculating an adjustment value for the intensity or frequency of the rehabilitation training, wherein the specific formula is as follows: Δs=β1 (e_total-e_total_old) +β2 (e_i-e_i_old), where Δs is the adjustment value of the intensity or frequency of the rehabilitation training, e_total_old and e_i_old are the values of e_total and e_i at the time of the last calculation, β1 and β2 are weights.
8. The intelligent rehabilitation and care device for chest outlet syndrome according to claim 7, wherein the settings of e_total_threshold and e_i_threshold are based on the specific condition of the patient and the experience of the doctor.
9. The intelligent rehabilitation and care device for chest outlet syndrome according to claim 1, wherein the patient interaction module comprises a user interface that allows the patient to enter own symptoms and sensations, including pain location, pain level, numbness or tingling frequency information.
10. The intelligent rehabilitation and care device for the thoracic outlet syndrome according to claim 1, wherein the patient interaction module provides real-time feedback to the patient through a feedback interface, including rehabilitation progress and outcome assessment results.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311386910.3A CN117133404B (en) | 2023-10-25 | 2023-10-25 | Intelligent rehabilitation nursing device to thorax export syndrome |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311386910.3A CN117133404B (en) | 2023-10-25 | 2023-10-25 | Intelligent rehabilitation nursing device to thorax export syndrome |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117133404A true CN117133404A (en) | 2023-11-28 |
| CN117133404B CN117133404B (en) | 2024-02-20 |
Family
ID=88861319
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311386910.3A Active CN117133404B (en) | 2023-10-25 | 2023-10-25 | Intelligent rehabilitation nursing device to thorax export syndrome |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117133404B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117442218A (en) * | 2023-12-25 | 2024-01-26 | 深圳市前海蛇口自贸区医院(深圳市南山区蛇口人民医院) | Muscle information detection device for thoracic outlet syndrome |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW510797B (en) * | 2001-11-13 | 2002-11-21 | Young-Hee Lee | Intramuscular stimulator |
| CN108136245A (en) * | 2015-07-23 | 2018-06-08 | 现代卫生有限公司 | Muscle treatment device |
| WO2020206179A1 (en) * | 2019-04-05 | 2020-10-08 | Baylor College Of Medicine | Method and system for detection and analysis of thoracic outlet syndrome (tos) |
| CN116705240A (en) * | 2023-06-14 | 2023-09-05 | 齐齐哈尔市第一医院 | Acupuncture rehabilitation effect quantification system based on rehabilitation state self-adaptive monitoring |
| CN116805525A (en) * | 2023-08-21 | 2023-09-26 | 营动智能技术(山东)有限公司 | Chronic disease informationized management method, system and storage medium |
-
2023
- 2023-10-25 CN CN202311386910.3A patent/CN117133404B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW510797B (en) * | 2001-11-13 | 2002-11-21 | Young-Hee Lee | Intramuscular stimulator |
| CN108136245A (en) * | 2015-07-23 | 2018-06-08 | 现代卫生有限公司 | Muscle treatment device |
| WO2020206179A1 (en) * | 2019-04-05 | 2020-10-08 | Baylor College Of Medicine | Method and system for detection and analysis of thoracic outlet syndrome (tos) |
| CN116705240A (en) * | 2023-06-14 | 2023-09-05 | 齐齐哈尔市第一医院 | Acupuncture rehabilitation effect quantification system based on rehabilitation state self-adaptive monitoring |
| CN116805525A (en) * | 2023-08-21 | 2023-09-26 | 营动智能技术(山东)有限公司 | Chronic disease informationized management method, system and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117442218A (en) * | 2023-12-25 | 2024-01-26 | 深圳市前海蛇口自贸区医院(深圳市南山区蛇口人民医院) | Muscle information detection device for thoracic outlet syndrome |
| CN117442218B (en) * | 2023-12-25 | 2024-03-22 | 深圳市前海蛇口自贸区医院(深圳市南山区蛇口人民医院) | Muscle information detection device for thoracic outlet syndrome |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117133404B (en) | 2024-02-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11682480B2 (en) | System and method for pre-action training and control | |
| He et al. | Real-time detection of acute cognitive stress using a convolutional neural network from electrocardiographic signal | |
| Xu et al. | Cluster-based analysis for personalized stress evaluation using physiological signals | |
| González-Franco et al. | Motor imagery based brain-computer interface: A study of the effect of positive and negative feedback | |
| CN117133404B (en) | Intelligent rehabilitation nursing device to thorax export syndrome | |
| Bao et al. | Automatically evaluating balance: a machine learning approach | |
| WO2023155435A1 (en) | Cognitive improvement training method and system based on neuromodulation | |
| Pedraza et al. | Pelvic muscle rehabilitation: a standardized protocol for pelvic floor dysfunction | |
| Zhang et al. | Fuzzy inference system based automatic Brunnstrom stage classification for upper-extremity rehabilitation | |
| WO2010129711A1 (en) | Devices, systems, and methods for evaluating vision and diagnosing and compensating impairment of vision | |
| Chen et al. | Scalp EEG-based pain detection using convolutional neural network | |
| KR102426939B1 (en) | User Customized Training System And Method For Improving Cognitive Using Cognitive Impairment Analysis By Virtual Reality Based Cognitive Game Score | |
| Wang et al. | A novel fatigue detection method for rehabilitation training of upper limb exoskeleton robot using multi-information fusion | |
| CN117153379B (en) | Prediction device for thoracic outlet syndrome | |
| CN117253616A (en) | Neurological rehabilitation degree evaluation method and system | |
| CN110720908A (en) | Muscle injury rehabilitation training system based on vision-myoelectricity biofeedback and rehabilitation training method applying same | |
| CN113614751A (en) | Electroencephalogram signal identification and extraction | |
| CN116312951B (en) | Exercise function assessment method and system based on multi-modal coupling analysis | |
| Zhou et al. | Upper-limb functional assessment after stroke using mirror contraction: A pilot study | |
| Yiu et al. | Fatigue-Related change in surface electromyographic activities of the perilaryngeal muscles | |
| Dhindsa et al. | Toward an open-ended BCI: a user-centered coadaptive design | |
| Wang et al. | Classification of human movements with and without spinal orthosis based on surface electromyogram signals | |
| CN110720909B (en) | Whole rehabilitation training system for waist and abdomen core muscle group based on myoelectric biofeedback and application thereof | |
| JP6749777B2 (en) | Rehabilitation equipment | |
| Henshaw | Improved brain-computer interface methods with application to gaming |
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 |