Rehabilitation nursing real-time monitoring system for patients with mobility disorder

Abstract

According to the rehabilitation nursing real-time monitoring system for the patients with the mobility disorder, a wearable device, a monitoring camera, a video processing module, an environment monitoring module and the like are integrated, a cloud data analysis function is achieved, and comprehensive tracking and evaluation of the rehabilitation process are achieved. The system continuously monitors the heart rate, the blood pressure and the activity amount of the patient through the wearable device, and accurately captures rehabilitation activities of the patient in combination with environment parameters and video analysis. The video processing module carries out image correction by using a calibration point and accurately tracks a joint motion track, and advanced feature extraction and fusion of physiological, motion and environmental data are carried out by using a deep learning model (LSTM, CNN), so that rehabilitation stages can be classified, rehabilitation types can be determined, and rehabilitation scores can be predicted. The system not only improves the quantitative evaluation ability of the rehabilitation effect, but also provides real-time monitoring, alarming and remote management functions through the user terminal, promotes doctor-patient interaction and implementation of a personalized rehabilitation plan, and brings innovation for rehabilitation management of the patient with the mobility disorder.

Description

Technical Field

[0001] The present disclosure relates to the field of medical rehabilitation technology, and in particular to a real-time monitoring system for rehabilitation care of patients with movement disorders. Background Art

[0002] With the rapid development of medical technology, rehabilitation medicine, as an important part of the medical and health system, has become increasingly important. Especially when facing the special group of patients with mobility impairments, traditional rehabilitation treatment methods often focus on on-site supervision and manual recording, which not only consumes a lot of human resources, but also has obvious limitations in monitoring continuity, accuracy, and personalized feedback. For example, the monitoring of patients' physiological parameters may be limited to regular clinical examinations and cannot capture immediate changes in daily activities; activity assessment relies on regular functional tests, which makes it difficult to reflect the progress or regression of rehabilitation in real time; and environmental factors such as temperature and humidity are often ignored in their impact on patient rehabilitation.

[0003] In recent years, with the rise of the Internet of Things (IoT), big data, artificial intelligence (AI) and cloud computing technologies, the medical and health field has ushered in unprecedented opportunities for change. The application of these technologies has made it possible to realize intelligent and precise rehabilitation care. For example, the development of wearable devices has made it possible to continuously and non-invasively monitor patients' vital signs; the advancement of video analysis and computer vision technology has provided new ways to accurately capture and analyze patients' movement behaviors; and cloud platforms and big data analysis can integrate multi-source heterogeneous data and conduct in-depth mining, providing a scientific basis for rehabilitation effect evaluation and personalized rehabilitation plan formulation.

[0004] However, despite significant technological advances, the current market lacks a comprehensive real-time monitoring system that can fully integrate the above-mentioned technological advantages and provide patients with mobility impairments with everything from physiological parameter monitoring, environmental adaptability assessment to motor function analysis, and even personalized rehabilitation recommendations. Some existing systems may only focus on a single dimension, such as focusing only on physiological parameter monitoring, or only providing simple video monitoring services, and fail to form a closed-loop rehabilitation management solution. In addition, these systems often neglect efficient interaction with patients, their families, and the medical team, lack effective remote monitoring and instant feedback mechanisms, and limit the optimization of rehabilitation effects and the effective use of medical resources.

[0005] Therefore, the development of a real-time monitoring system for rehabilitation care of patients with mobility impairments that integrates wearable devices, high-definition video surveillance, environmental perception, cloud data analysis and decision support is of great significance for promoting the modernization of rehabilitation medicine, improving the quality and efficiency of rehabilitation treatment, and meeting the diversified and personalized rehabilitation needs of patients. Summary of the invention

[0006] In order to solve the above problems, the present invention provides a real-time monitoring system for rehabilitation nursing of patients with movement disorders, comprising:

[0007] Monitoring system host: As the core of the system, it is responsible for receiving, processing and coordinating data transmission from each module, and communicating with the cloud module to realize remote storage and analysis of data.

[0008] User terminal module: installed on medical staff workstations or family members' mobile devices, providing real-time monitoring data display, alarm reception and remote operation interface.

[0009] Wearable device module: includes heart rate detection unit, blood pressure detection unit and activity detection unit, which encrypts and transmits the patient's heart rate, blood pressure and activity data to the monitoring system host through a wireless communication module (such as Bluetooth or Wi-Fi).

[0010] Monitoring camera module: installed in the patient's activity area, it captures the patient's movement images, combines calibration points for image correction and motion analysis, and provides visual basis for rehabilitation assessment.

[0011] Calibration point module: equipped with visual feature encoding information for image correction to ensure the accuracy of motion capture and the precision of spatial positioning.

[0012] Video processing module: Use image recognition technology to process images collected by monitoring cameras, extract patient movement trajectories, and provide data support for rehabilitation effect evaluation.

[0013] Environmental monitoring module: monitors the temperature and humidity of the patient's environment to ensure the suitability of the rehabilitation environment.

[0014] Data storage module: located in the local server, stores all monitoring data and analysis results for long-term tracking and analysis.

[0015] Cloud module: Deployed in a remote data center, it not only provides data backup and storage, but also runs the rehabilitation analysis model to classify rehabilitation stages, determine rehabilitation types, and calculate rehabilitation scores based on comprehensive data. The system is as follows:

[0016] A real-time monitoring system for rehabilitation nursing of patients with movement disorders, comprising a monitoring system host, a user terminal module, a monitoring camera, a wearable device, a video processing module, a calibration point, a cloud module, an environmental monitoring module and a data storage module; the monitoring system host is connected with the user terminal module, the monitoring camera, the wearable device, the video processing module, the calibration point, the cloud module, the environmental monitoring module and the data storage module;

[0017] The wearable device module is worn on the patient to collect the patient's heart rate, blood pressure and activity level in real time;

[0018] The monitoring camera module is installed in the patient's activity area to collect the patient's time-flow image and send it to the detection system host;

[0019] The calibration points are fixed at fixed positions in the patient's activity area to provide spatial coordinate references and improve the accuracy of motion capture and positioning;

[0020] The video processing module is used to process the time stream images collected by the monitoring camera module and send the processed images to the monitoring system host;

[0021] The environmental monitoring module is installed in different corners of the patient's activity area to detect the temperature T and humidity Rh of the environment in real time;

[0022] The storage module is installed on the local server to store all monitoring data and analysis results for later reference and mining;

[0023] The cloud module is deployed in a remote data center to provide cloud data storage and cloud data analysis functions for the monitoring system host;

[0024] User terminal modules are installed on medical staff workstations, wards or family members’ mobile devices to display real-time monitoring data, receive alarm information, and implement remote operation and management;

[0025] The monitoring system host obtains data from the wearable device module, monitoring camera module and environmental monitoring module, and sends the data to the cloud module. The cloud module runs the rehabilitation analysis model, which calculates and determines the patient's rehabilitation stage and rehabilitation type, and gives the patient's rehabilitation score, and sends the specific rehabilitation stage, rehabilitation type and rehabilitation score to the user terminal module.

[0026] It includes a heart rate detection unit, which is configured to continuously collect and digitize the patient's ECG signal in real time, accurately calculate and upload the patient's heart rate parameter HR to the monitoring system host;

[0027] The blood pressure detection unit uses non-invasive or minimally invasive technology to measure the patient's blood pressure parameters in real time, including systolic blood pressure SBP and diastolic blood pressure DBP, and sends the measurement results to the monitoring system host;

[0028] Activity detection unit, integrating accelerometer and gyroscope, records and quantifies the patient's activity status information, including the number of steps S, activity intensity I and movement change trajectory D;

[0029] The wireless communication module uses Bluetooth or Wi-Fi to encrypt the processed patient heart rate parameters HR, blood pressure parameters SBP, DBP and activity parameters S, I, D and transmit them to the monitoring system host in real time.

[0030] The calibration point module is fixedly installed at the key geometric position in the patient's activity area, and each calibration point has visual feature coding information;

[0031] The monitoring camera module sends the collected time stream image including the calibration points to the monitoring system host; the monitoring system host sends the time stream image to the video processing module, and the video processing module uses image recognition technology and computer vision algorithms to perform calibration and correction processing on the received time stream image; the specific process of the correction processing is as follows:

[0032] 1) Perform real-time analysis on the time stream image sequence and extract the position information of each calibration point in the image through template matching or feature point detection technology;

[0033] 2) Based on the perspective transformation principle, the position of the calibration point in the two-dimensional image coordinate system is converted to a pre-set three-dimensional world coordinate system to achieve accurate mapping of the image to the real space;

[0034] 3) By comparing the observed position of the calibration point in the image with its known position in the actual space, the camera's internal and external parameters are corrected using the least squares method to achieve effective correction of the camera's field of view and lens distortion;

[0035] Among them: internal parameters include focal length and principal point coordinates, and external parameters include rotation matrix and translation matrix.

[0036] The surface of the calibration point is provided with a two-dimensional code and an edge mark; the two-dimensional code corresponds to the unique code of the calibration point, and the edge mark is used to assist in identifying the edge of the calibration point.

[0037] The video processing module recognizes the patient's joint motion trajectory based on the time stream image. The specific steps include:

[0038] Foot positioning: By analyzing multiple frames of images of the patient's feet touching the ground when standing or walking, contour recognition and shape matching algorithms are used to determine the position of each foot in the image, and then the precise coordinates of the patient's feet in three-dimensional space are calculated and determined through the spatial coordinate system of the calibration points;

[0039] Determination of center of mass coordinates: Based on the known spatial coordinates of the two feet, image processing and geometric analysis methods are used to identify the patient's body contour, calculate the center of mass position, and define the projection point of the center of mass on the horizontal plane as the center point of the projection line of the two feet's coordinates on the horizontal plane, thereby determining the patient's center of mass three-dimensional coordinates;

[0040] Determination of spatial coordinates of feature points: Based on the foot coordinates and center of mass coordinates, a skeleton estimation algorithm, OpenPose algorithm, is used to track and predict other feature points of the patient in continuous time stream images: ankle, knee, hip, shoulder, elbow and wrist. Through the spatial relationship and kinematic model of these points, their coordinates in three-dimensional space are calculated and determined.

[0041] The spatial coordinates of the feature points are determined, including:

[0042] Initial feature point positioning: First, based on the determined foot coordinates and center of mass coordinates, the pre-trained human key point detection model is used to estimate the initial spatial coordinates of the ankle, knee, hip, shoulder, elbow, and wrist joints;

[0043] Optimization of spatiotemporal continuity: For each feature point, apply the optical flow method or continuous frame matching technology in the time-continuous image sequence to track the position changes of these feature points at different time points;

[0044] Motion trajectory generation: Based on the dynamic tracking results of the feature point positions in continuous frames, the three-dimensional spatial motion trajectory of each joint of the patient is constructed; for each feature point, the position change in the time dimension is smoothed by interpolation or fitting methods to obtain a continuous and smooth motion path.

[0045] The cloud module runs the rehabilitation analysis model as follows:

[0046] Timeline alignment: unify the timestamps of the heart rate parameters HR, blood pressure parameters SBP and DBP, activity parameters S, I, D obtained in real time by the wearable device module; the ambient temperature T and humidity Rh obtained by the environmental monitoring module; and the motion path data of the feature points obtained by the monitoring camera module; ensure that the data is standardized according to the unified timestamp and that the timeline is aligned;

[0047] Data preprocessing: missing value filling, outlier detection and processing, and data standardization are performed on the aligned time series data;

[0048] Feature extraction: LSTM network is used to process time series physiological index data to obtain physiological features, CNN is used to process motion paths to extract motion features, and statistical features are extracted from environmental data;

[0049] Feature fusion: The extracted physiological features, motion features, and environmental features are integrated to form a comprehensive feature vector, and the attention mechanism is used for weighted fusion;

[0050] Rehabilitation analysis and evaluation: Support vector machine was used to classify the rehabilitation stages, K-means clustering algorithm was used to determine the rehabilitation type, and gradient boosting regression tree was used to calculate the rehabilitation score.

[0051] The rehabilitation analysis model is constructed as follows:

[0052] Collect monitoring parameters of patients with movement disorders of different ages, genders, and etiology backgrounds to ensure that the data set includes patients at different stages of rehabilitation, different rehabilitation types, and different rehabilitation scores;

[0053] The preprocessed data set is divided into a training set, a validation set, and a test set; the monitoring data is used as input; and the rehabilitation analysis model is trained with different rehabilitation stages, different rehabilitation types, and different rehabilitation scores as output;

[0054] The monitoring data includes: heart rate parameters HR, blood pressure parameters SBP and DBP, activity parameters S, I, D acquired in real time by the wearable device module, ambient temperature T and humidity Rh acquired by the environmental monitoring module, and the motion path of the feature points acquired by the monitoring camera module;

[0055] Among them: the rehabilitation stages include the initial stage, the middle stage, and the final stage; the rehabilitation types include the rapid recovery type, the ordinary recovery type, and the slow recovery type;

[0056] The rehabilitation score adopts a scoring scale of 1-100, where 1 represents the weakest rehabilitation effect and the rehabilitation care plan needs to be adjusted; 100 represents the best rehabilitation effect and no adjustment of the rehabilitation care plan is required.

[0057] The beneficial effects of the present invention are:

[0058] Through integrated wearable devices, monitoring cameras, and environmental monitoring modules, this system achieves comprehensive, real-time monitoring of the physiological parameters (such as heart rate, blood pressure, activity level), environmental conditions (temperature, humidity), and exercise behavior of patients with mobility impairments. This not only improves the continuity and accuracy of monitoring, but also makes it possible to promptly detect health abnormalities and environmental discomfort, ensuring the safety and effectiveness of the rehabilitation process.

[0059] The system uses advanced image recognition and computer vision technology, combined with human kinematics analysis, to accurately track the patient's joint movement trajectory, providing an intuitive and visual evaluation basis for rehabilitation progress. Combining physiological data and environmental factors, the rehabilitation analysis model run by the cloud module can perform detailed rehabilitation stage classification, rehabilitation type determination and rehabilitation scoring for patients, providing a scientific basis for the formulation of personalized rehabilitation plans.

[0060] The cloud module uses complex data processing algorithms, such as time series analysis, feature extraction and fusion, to effectively integrate cross-dimensional data, providing strong support for in-depth analysis of rehabilitation effects. This intelligent analysis based on big data can not only accurately assess the current rehabilitation status, but also predict rehabilitation trends, providing forward-looking decision support for adjusting rehabilitation strategies.

[0061] The establishment of the user terminal module allows medical staff and family members to remotely view the patient's status in real time, receive alarm information, and even participate in rehabilitation management, which strengthens doctor-patient communication and improves nursing efficiency. It also reduces the burden on patients due to frequent travel to medical institutions and enhances patients' rehabilitation experience and sense of participation.

[0062] Through intelligent and remote rehabilitation nursing models, the present invention helps optimize the allocation of medical resources, especially in areas with tight medical resources or in remote areas, enabling more patients with mobility impairments to enjoy high-quality rehabilitation services, and promoting the improvement of medical equity and accessibility. Through technical integration and innovation, the present invention not only improves the quality and efficiency of rehabilitation, but also enhances the quality of life of patients, which is a major advancement in the field of modern medical rehabilitation. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0064] Attached Figure 1 It is a schematic diagram of the overall structure of the present invention;

[0065] Attached Figure 2 Schematic diagram of the arrangement of calibration points of the present invention. DETAILED DESCRIPTION

[0066] Embodiment 1:

[0067] See also Figure 1 and Figure 2 , the present invention provides a real-time monitoring system for rehabilitation nursing of patients with movement disorders, including a monitoring system host, a user terminal module, a monitoring camera, a wearable device, a video processing module, a calibration point, a cloud module, an environmental monitoring module and a data storage module; the monitoring system host and the user terminal module, the monitoring camera, the wearable device, the video processing module, the calibration point, the cloud module, the environmental monitoring module and the data storage module are connected;

[0068] The wearable device module is worn on the patient to collect the patient's heart rate, blood pressure and activity level in real time;

[0069] The monitoring camera module is installed in the patient's activity area to collect the patient's time-flow image and send it to the detection system host;

[0070] The calibration points are fixed at fixed positions in the patient's activity area to provide spatial coordinate references and improve the accuracy of motion capture and positioning;

[0071] The video processing module is used to process the time stream images collected by the monitoring camera module and send the processed images to the monitoring system host;

[0072] The environmental monitoring module is installed in different corners of the patient's activity area to detect the temperature T and humidity Rh of the environment in real time;

[0073] The storage module is installed on the local server to store all monitoring data and analysis results for later reference and mining;

[0074] The cloud module is deployed in a remote data center to provide cloud data storage and cloud data analysis functions for the monitoring system host;

[0075] User terminal modules are installed on medical staff workstations, wards or family members’ mobile devices to display real-time monitoring data, receive alarm information, and implement remote operation and management;

[0076] The monitoring system host obtains data from the wearable device module, monitoring camera module and environmental monitoring module, and sends the data to the cloud module. The cloud module runs the rehabilitation analysis model, which calculates and determines the patient's rehabilitation stage and rehabilitation type, and gives the patient's rehabilitation score, and sends the specific rehabilitation stage, rehabilitation type and rehabilitation score to the user terminal module.

[0077] It includes a heart rate detection unit, which is configured to continuously collect and digitize the patient's ECG signal in real time, accurately calculate and upload the patient's heart rate parameter HR to the monitoring system host;

[0078] The blood pressure detection unit uses non-invasive or minimally invasive technology to measure the patient's blood pressure parameters in real time, including systolic blood pressure SBP and diastolic blood pressure DBP, and sends the measurement results to the monitoring system host;

[0079] Activity detection unit, integrating accelerometer and gyroscope, records and quantifies the patient's activity status information, including the number of steps S, activity intensity I and movement change trajectory D;

[0080] The wireless communication module uses Bluetooth or Wi-Fi to encrypt the processed patient heart rate parameters HR, blood pressure parameters SBP, DBP and activity parameters S, I, D and transmit them to the monitoring system host in real time.

[0081] The calibration point module is fixedly installed at the key geometric position in the patient's activity area, and each calibration point has visual feature coding information;

[0082] The monitoring camera module sends the collected time stream image including the calibration points to the monitoring system host; the monitoring system host sends the time stream image to the video processing module, and the video processing module uses image recognition technology and computer vision algorithms to perform calibration and correction processing on the received time stream image; the specific process of the correction processing is as follows:

[0083] 1) Perform real-time analysis on the time stream image sequence and extract the position information of each calibration point in the image through template matching or feature point detection technology;

[0084] 2) Based on the perspective transformation principle, the position of the calibration point in the two-dimensional image coordinate system is converted to a pre-set three-dimensional world coordinate system to achieve accurate mapping of the image to the real space;

[0085] 3) By comparing the observed position of the calibration point in the image with its known position in the actual space, the camera's internal and external parameters are corrected using the least squares method to achieve effective correction of the camera's field of view and lens distortion;

[0086] Among them: internal parameters include focal length and principal point coordinates, and external parameters include rotation matrix and translation matrix.

[0087] The surface of the calibration point is provided with a two-dimensional code and an edge mark; the two-dimensional code corresponds to the unique code of the calibration point, and the edge mark is used to assist in identifying the edge of the calibration point.

[0088] The video processing module recognizes the patient's joint motion trajectory based on the time stream image. The specific steps include:

[0089] Foot positioning: By analyzing multiple frames of images of the patient's feet touching the ground when standing or walking, contour recognition and shape matching algorithms are used to determine the position of each foot in the image, and then the precise coordinates of the patient's feet in three-dimensional space are calculated and determined through the spatial coordinate system of the calibration points;

[0090] Determination of center of mass coordinates: Based on the known spatial coordinates of the two feet, image processing and geometric analysis methods are used to identify the patient's body contour, calculate the center of mass position, and define the projection point of the center of mass on the horizontal plane as the center point of the projection line of the two feet's coordinates on the horizontal plane, thereby determining the patient's center of mass three-dimensional coordinates;

[0091] Determination of spatial coordinates of feature points: Based on the foot coordinates and center of mass coordinates, a skeleton estimation algorithm, OpenPose algorithm, is used to track and predict other feature points of the patient in continuous time stream images: ankle, knee, hip, shoulder, elbow and wrist. Through the spatial relationship and kinematic model of these points, their coordinates in three-dimensional space are calculated and determined.

[0092] The spatial coordinates of the feature points are determined, including:

[0093] Initial feature point positioning: First, based on the determined foot coordinates and center of mass coordinates, the pre-trained human key point detection model is used to estimate the initial spatial coordinates of the ankle, knee, hip, shoulder, elbow, and wrist joints;

[0094] Optimization of spatiotemporal continuity: For each feature point, apply the optical flow method or continuous frame matching technology in the time-continuous image sequence to track the position changes of these feature points at different time points;

[0095] Motion trajectory generation: Based on the dynamic tracking results of the feature point positions in continuous frames, the three-dimensional spatial motion trajectory of each joint of the patient is constructed; for each feature point, the position change in the time dimension is smoothed by interpolation or fitting methods to obtain a continuous and smooth motion path.

[0096] The cloud module runs the rehabilitation analysis model as follows:

[0097] Timeline alignment: unify the timestamps of the heart rate parameters HR, blood pressure parameters SBP and DBP, activity parameters S, I, D obtained in real time by the wearable device module; the ambient temperature T and humidity Rh obtained by the environmental monitoring module; and the motion path data of the feature points obtained by the monitoring camera module; ensure that the data is standardized according to the unified timestamp and that the timeline is aligned;

[0098] Data preprocessing: missing value filling, outlier detection and processing, and data standardization are performed on the aligned time series data;

[0099] Feature extraction: LSTM network is used to process time series physiological index data to obtain physiological features, CNN is used to process motion paths to extract motion features, and statistical features are extracted from environmental data;

[0100] Feature fusion: The extracted physiological features, motion features, and environmental features are integrated to form a comprehensive feature vector, and the weighted fusion is performed using an attention mechanism;

[0101] Rehabilitation analysis and evaluation: Support vector machine was used to classify the rehabilitation stages, K-means clustering algorithm was used to determine the rehabilitation type, and gradient boosting regression tree was used to calculate the rehabilitation score.

[0102] The rehabilitation analysis model is constructed as follows:

[0103] Collect monitoring parameters of patients with movement disorders of different ages, genders, and etiology backgrounds to ensure that the data set includes patients at different stages of rehabilitation, different rehabilitation types, and different rehabilitation scores;

[0104] The preprocessed data set is divided into a training set, a validation set, and a test set; the monitoring data is used as input; and the rehabilitation analysis model is trained with different rehabilitation stages, different rehabilitation types, and different rehabilitation scores as output;

[0105] The monitoring data includes: heart rate parameters HR, blood pressure parameters SBP and DBP, activity parameters S, I, D acquired in real time by the wearable device module, ambient temperature T and humidity Rh acquired by the environmental monitoring module, and the motion path of the feature points acquired by the monitoring camera module;

[0106] Among them: the rehabilitation stages include the initial stage, the middle stage, and the final stage; the rehabilitation types include the rapid recovery type, the ordinary recovery type, and the slow recovery type;

[0107] The rehabilitation score adopts a scoring scale of 1-100, where 1 represents the weakest rehabilitation effect and the rehabilitation care plan needs to be adjusted; 100 represents the best rehabilitation effect and no adjustment of the rehabilitation care plan is required.

[0108] The present invention uses deep learning technology in the rehabilitation analysis model running in the cloud module to construct a multi-level neural network structure, the specific levels include but are not limited to the following key parts:

[0109] Input Layer:

[0110] Receive and standardize various data: heart rate (HR), blood pressure (SBP & DBP), activity parameters (number of steps S, activity intensity I, movement change trajectory D) obtained from wearable devices, temperature (T) and humidity (Rh) from environmental monitoring, and feature point motion path data output by the video processing module. After time axis alignment and preprocessing, these data are used as input to the model.

[0111] Feature extraction layer:

[0112] Physiological feature extraction: Long short-term memory network (LSTM) is used to process time series data (such as heart rate and blood pressure changes), capture time-dependent features, and extract dynamic features that reflect the patient's physiological state.

[0113] Motion feature extraction: Use convolutional neural network (CNN) to process the motion path image of feature points to capture spatial features and motion patterns, such as the movement patterns of joints.

[0114] Environmental feature extraction: Statistical analysis of environmental data is performed to extract the characteristics of environmental influencing factors related to rehabilitation.

[0115] Feature fusion layer:

[0116] The above-extracted physiological features, motion features, and environmental features are weighted and fused through the attention mechanism to form a comprehensive feature vector. This layer aims to integrate multi-source information and enhance the model's ability to understand complex rehabilitation situations.

[0117] Prediction / Classification Layer:

[0118] Rehabilitation stage classification: Use support vector machine (SVM) to classify the fused features to determine the patient's current rehabilitation stage (early, middle, and final).

[0119] Determination of rehabilitation type: Patients were clustered using the K-means clustering algorithm to identify their rehabilitation types (rapid recovery type, normal recovery type, slow recovery type).

[0120] Rehabilitation score prediction: The gradient boosted regression tree (GBRT) model is applied to predict the patient's rehabilitation score based on the comprehensive feature vector and quantify the rehabilitation effect.

[0121] Output layer:

[0122] Provide the final rehabilitation stage classification, rehabilitation type and rehabilitation score, provide medical staff with clear rehabilitation assessment results, and guide the formulation and adjustment of personalized rehabilitation care plans.

[0123] In summary, the present invention integrates multi-module technology to realize intelligent monitoring of the patient's rehabilitation process. The monitoring system host is connected with the user terminal module, monitoring camera, wearable device, etc., to build an efficient platform for data intercommunication.

[0124] The wearable device module is worn on the patient to collect heart rate, blood pressure and activity in real time, continuously monitor physiological parameters, and respond to changes in health status in real time; the monitoring camera module is installed in the activity area to capture time-flow images and transmit them to the host, providing visual feedback to assist in behavior and environmental adaptability analysis; the calibration points are deployed in fixed positions as spatial references to improve motion capture accuracy, enhance positioning reliability, and ensure accurate motion analysis; the video processing module processes image data, optimizes it and transmits it to the host, and uses image recognition technology to refine motion analysis and behavior pattern recognition; the environmental monitoring module is distributed in the corner to detect temperature and humidity in real time, monitor environmental comfort, and ensure that the rehabilitation environment is suitable; the data storage module saves all monitoring information for easy review and research, establishes a comprehensive rehabilitation process archive, and supports in-depth data mining; the cloud module provides remote data access and analysis services, realizes cross-regional resource sharing, and accelerates rehabilitation strategy decision-making; the user terminal displays real-time data and alarms, supports remote management, and enhances the participation and intervention capabilities of medical staff and family members; the monitoring system host integrates data and sends it to the cloud, uses the rehabilitation analysis model to evaluate the rehabilitation stage and type, gives scores, scientifically guides personalized rehabilitation paths, and improves rehabilitation results.

[0125] Thus far, the description of the above-described embodiments is provided for the purpose of illustration and description. It is not intended to be exhaustive or to limit the present disclosure. The individual elements or features of a specific embodiment are generally not subject to the limitations of the specific embodiment, but when applicable, they can be interchanged and used for selected embodiments even if not specifically shown or described. In many respects, the same element or feature also can be changed. This variation is not considered to be a departure from the present disclosure, and all such modifications are intended to be included in the scope of the present disclosure.

[0126] Example embodiments are provided so that the present disclosure will be thorough and the scope will be fully conveyed to those skilled in the art. In order to thoroughly understand the embodiments of the present disclosure, numerous details are set forth, such as examples of specific parts, devices, and methods. Obviously, for those skilled in the art, it is not necessary to use specific details, the example embodiments can be implemented in many different forms, and neither should be construed as limiting the scope of the present disclosure. In certain example embodiments, well-known processes, well-known device structures, and well-known technologies are not described in detail.

[0127] Here, specialized vocabulary is used only for the purpose of describing specific example embodiments, and is not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "a" and "the" used herein may be intended to include plural forms as well. The terms "including" and "having" are inclusive, and therefore specify the presence of the claimed features, wholes, steps, operations, elements and / or components, but do not exclude the presence or additional presence of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof. Unless the order of execution is clearly indicated, the method steps, processing and operations described herein are not interpreted as necessarily needing to be performed in the specific order discussed and shown. It should also be understood that additional or optional steps may be adopted.

Claims

1. A real-time monitoring system for rehabilitation nursing of patients with movement disorders, comprising a monitoring system host, a user terminal module, a monitoring camera, a wearable device, a video processing module, a calibration point, a cloud module, an environmental monitoring module and a data storage module; the monitoring system host is connected with the user terminal module, the monitoring camera, the wearable device, the video processing module, the calibration point, the cloud module, the environmental monitoring module and the data storage module; The wearable device module is worn on the patient to collect the patient's heart rate, blood pressure and activity level in real time; the monitoring camera module is installed in the patient's activity area to collect the patient's time stream image and send it to the detection system host; The calibration points are fixed at fixed positions in the patient's activity area to provide spatial coordinate references and improve the accuracy of motion capture and positioning; The video processing module is used to process the time stream images collected by the monitoring camera module and send the processed images to the monitoring system host; The environmental monitoring module is installed in different corners of the patient's activity area to detect the temperature T and humidity Rh of the environment in real time; The storage module is installed on the local server to store all monitoring data and analysis results for later reference and mining; The cloud module is deployed in a remote data center to provide cloud data storage and cloud data analysis functions for the monitoring system host; User terminal modules are installed on medical staff workstations, wards or family members’ mobile devices to display real-time monitoring data, receive alarm information, and implement remote operation and management; The monitoring system host obtains data from the wearable device module, monitoring camera module and environmental monitoring module, and sends the data to the cloud module. The cloud module runs the rehabilitation analysis model, which calculates and determines the patient's rehabilitation stage and rehabilitation type, and gives the patient's rehabilitation score, and sends the specific rehabilitation stage, rehabilitation type and rehabilitation score to the user terminal module.

2. The real-time monitoring system for rehabilitation care of patients with movement disorders according to claim 1, Features: It includes a heart rate detection unit, which is configured to continuously collect and digitize the patient's ECG signal in real time, accurately calculate and upload the patient's heart rate parameter HR to the monitoring system host; The blood pressure detection unit uses non-invasive or minimally invasive technology to measure the patient's blood pressure parameters in real time, including systolic blood pressure SBP and diastolic blood pressure DBP, and sends the measurement results to the monitoring system host; Activity detection unit, integrating accelerometer and gyroscope, records and quantifies the patient's activity status information, including the number of steps S, activity intensity I and movement change trajectory D; The wireless communication module uses Bluetooth or Wi-Fi to encrypt the processed patient heart rate parameters HR, blood pressure parameters SBP, DBP and activity parameters S, I, D and transmit them to the monitoring system host in real time.

3. The real-time monitoring system for rehabilitation care of patients with movement disorders according to claim 1, Features: The calibration point module is fixedly installed at the key geometric position in the patient's activity area, and each calibration point has visual feature coding information; The monitoring camera module sends the collected time stream image including the calibration points to the monitoring system host; the monitoring system host sends the time stream image to the video processing module, and the video processing module uses image recognition technology and computer vision algorithms to perform calibration and correction processing on the received time stream image; the specific process of the correction processing is as follows: 1) Perform real-time analysis on the time stream image sequence and extract the position information of each calibration point in the image through template matching or feature point detection technology; 2) Based on the perspective transformation principle, the position of the calibration point in the two-dimensional image coordinate system is converted to a pre-set three-dimensional world coordinate system to achieve accurate mapping of the image to the real space; 3) By comparing the observed position of the calibration point in the image with its known position in the actual space, the camera's internal and external parameters are corrected using the least squares method to achieve effective correction of the camera's field of view and lens distortion; Among them: internal parameters include focal length and principal point coordinates, and external parameters include rotation matrix and translation matrix.

4. The real-time monitoring system for rehabilitation care of patients with movement disorders according to claim 3, Features: The surface of the calibration point is provided with a two-dimensional code and an edge mark; the two-dimensional code corresponds to the unique code of the calibration point, and the edge mark is used to assist in identifying the edge of the calibration point.

5. The real-time monitoring system for rehabilitation care of patients with movement disorders according to claim 3, Features: The video processing module recognizes the patient's joint motion trajectory based on the time stream image. The specific steps include: Foot positioning: By analyzing multiple frames of images of the patient's feet touching the ground when standing or walking, contour recognition and shape matching algorithms are used to determine the position of each foot in the image, and then the precise coordinates of the patient's feet in three-dimensional space are calculated and determined through the spatial coordinate system of the calibration points; Determination of center of mass coordinates: Based on the known spatial coordinates of the two feet, image processing and geometric analysis methods are used to identify the patient's body contour, calculate the center of mass position, and define the projection point of the center of mass on the horizontal plane as the center point of the projection line of the two feet's coordinates on the horizontal plane, thereby determining the patient's center of mass three-dimensional coordinates; Determination of spatial coordinates of feature points: Based on the foot coordinates and center of mass coordinates, a skeleton estimation algorithm, OpenPose algorithm, is used to track and predict other feature points of the patient in continuous time stream images: ankle, knee, hip, shoulder, elbow and wrist. Through the spatial relationship and kinematic model of these points, their coordinates in three-dimensional space are calculated and determined.

6. The real-time monitoring system for rehabilitation care of patients with movement disorders according to claim 5, Features: The spatial coordinates of the feature points are determined, including: Initial feature point positioning: First, based on the determined foot coordinates and center of mass coordinates, the pre-trained human key point detection model is used to estimate the initial spatial coordinates of the ankle, knee, hip, shoulder, elbow, and wrist joints; Optimization of spatiotemporal continuity: For each feature point, apply the optical flow method or continuous frame matching technology in the time-continuous image sequence to track the position changes of these feature points at different time points; Motion trajectory generation: Based on the dynamic tracking results of the feature point positions in continuous frames, the three-dimensional spatial motion trajectory of each joint of the patient is constructed; for each feature point, the position change in the time dimension is smoothed by interpolation or fitting methods to obtain a continuous and smooth motion path.

7. The real-time monitoring system for rehabilitation care of patients with movement disorders according to claim 6, Features: The cloud module runs the rehabilitation analysis model as follows: Timeline alignment: the heart rate parameters HR, blood pressure parameters SBP and DBP, activity parameters S, I, D obtained in real time by the wearable device module; the ambient temperature T and humidity Rh obtained by the environmental monitoring module; The timestamps of the motion path data of the feature points acquired by the monitoring camera module are unified; the data is standardized according to the unified timestamps and the time axis is aligned; Data preprocessing: missing value filling, outlier detection and processing, and data standardization are performed on the aligned time series data; Feature extraction: LSTM network is used to process time series physiological index data to obtain physiological features, CNN is used to process motion paths to extract motion features, and statistical features are extracted from environmental data; Feature fusion: The extracted physiological features, motion features, and environmental features are integrated to form a comprehensive feature vector, and the attention mechanism is used for weighted fusion; Rehabilitation analysis and evaluation: Support vector machine was used to classify the rehabilitation stages, K-means clustering algorithm was used to determine the rehabilitation type, and gradient boosting regression tree was used to calculate the rehabilitation score.

8. The real-time monitoring system for rehabilitation care of patients with movement disorders according to claim 7, Features: The rehabilitation analysis model is constructed as follows: Collect monitoring parameters of patients with movement disorders of different ages, genders, and etiology backgrounds to ensure that the data set includes patients at different stages of rehabilitation, different rehabilitation types, and different rehabilitation scores; Divide the preprocessed dataset into training set, validation set and test set; Using monitoring data as input; Training the rehabilitation analysis model with different rehabilitation stages, different rehabilitation types and different rehabilitation scores as output; The monitoring data includes: heart rate parameters HR, blood pressure parameters SBP and DBP, activity parameters S, I, D acquired in real time by the wearable device module, ambient temperature T and humidity Rh acquired by the environmental monitoring module, and the motion path of the feature points acquired by the monitoring camera module; Among them: the rehabilitation stages include the initial stage, the middle stage, and the final stage; the rehabilitation types include the rapid recovery type, the ordinary recovery type, and the slow recovery type; The rehabilitation score adopts a scoring scale of 1-100, where 1 represents the weakest rehabilitation effect and the rehabilitation care plan needs to be adjusted; 100 represents the best rehabilitation effect and no adjustment of the rehabilitation care plan is required.

Images