CN118592960B - A knee arthritis decompression correction monitoring system - Google Patents

A knee arthritis decompression correction monitoring system Download PDF

Info

Publication number
CN118592960B
CN118592960B CN202410550155.6A CN202410550155A CN118592960B CN 118592960 B CN118592960 B CN 118592960B CN 202410550155 A CN202410550155 A CN 202410550155A CN 118592960 B CN118592960 B CN 118592960B
Authority
CN
China
Prior art keywords
data
pressure
sensor
monitoring
pulse signal
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202410550155.6A
Other languages
Chinese (zh)
Other versions
CN118592960A (en
Inventor
亓攀
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Rehabilitation Research Center
Original Assignee
China Rehabilitation Research Center
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China Rehabilitation Research Center filed Critical China Rehabilitation Research Center
Priority to CN202410550155.6A priority Critical patent/CN118592960B/en
Publication of CN118592960A publication Critical patent/CN118592960A/en
Application granted granted Critical
Publication of CN118592960B publication Critical patent/CN118592960B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/22—Ergometry; Measuring muscular strength or the force of a muscular blow
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/0002—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Measuring devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor or mobility of a limb
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Measuring devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor or mobility of a limb
    • A61B5/1118—Determining activity level
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Measuring devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor or mobility of a limb
    • A61B5/1126—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor or mobility of a limb using a particular sensing technique
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/45—For evaluating or diagnosing the musculoskeletal system or teeth
    • A61B5/4538—Evaluating a particular part of the muscoloskeletal system or a particular medical condition
    • A61B5/4585—Evaluating the knee
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/48—Other medical applications
    • A61B5/4851—Prosthesis assessment or monitoring
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
    • A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
    • A61B5/6802—Sensor mounted on worn items
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
    • A61B5/6846—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be brought in contact with an internal body part, i.e. invasive
    • A61B5/6867—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be brought in contact with an internal body part, i.e. invasive specially adapted to be attached or implanted in a specific body part
    • A61B5/6878—Bone
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
    • A61B5/6846—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be brought in contact with an internal body part, i.e. invasive
    • A61B5/6885—Monitoring or controlling sensor contact pressure
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61F—FILTERS IMPLANTABLE INTO BLOOD VESSELS; PROSTHESES; DEVICES PROVIDING PATENCY TO, OR PREVENTING COLLAPSING OF, TUBULAR STRUCTURES OF THE BODY, e.g. STENTS; ORTHOPAEDIC, NURSING OR CONTRACEPTIVE DEVICES; FOMENTATION; TREATMENT OR PROTECTION OF EYES OR EARS; BANDAGES, DRESSINGS OR ABSORBENT PADS; FIRST-AID KITS
    • A61F2/00—Filters implantable into blood vessels; Prostheses, i.e. artificial substitutes or replacements for parts of the body; Appliances for connecting them with the body; Devices providing patency to, or preventing collapsing of, tubular structures of the body, e.g. stents
    • A61F2/02—Prostheses implantable into the body
    • A61F2/30—Joints
    • A61F2/46—Special tools for implanting artificial joints
    • A61F2/4657—Measuring instruments used for implanting artificial joints
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/0985—Hyperparameter optimisation; Meta-learning; Learning-to-learn
    • 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
    • G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
    • G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
    • G16H40/63—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for local operation
    • 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
    • G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
    • G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
    • G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
    • 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
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61F—FILTERS IMPLANTABLE INTO BLOOD VESSELS; PROSTHESES; DEVICES PROVIDING PATENCY TO, OR PREVENTING COLLAPSING OF, TUBULAR STRUCTURES OF THE BODY, e.g. STENTS; ORTHOPAEDIC, NURSING OR CONTRACEPTIVE DEVICES; FOMENTATION; TREATMENT OR PROTECTION OF EYES OR EARS; BANDAGES, DRESSINGS OR ABSORBENT PADS; FIRST-AID KITS
    • A61F2/00—Filters implantable into blood vessels; Prostheses, i.e. artificial substitutes or replacements for parts of the body; Appliances for connecting them with the body; Devices providing patency to, or preventing collapsing of, tubular structures of the body, e.g. stents
    • A61F2/02—Prostheses implantable into the body
    • A61F2/30—Joints
    • A61F2/46—Special tools for implanting artificial joints
    • A61F2/4657—Measuring instruments used for implanting artificial joints
    • A61F2002/4666—Measuring instruments used for implanting artificial joints for measuring force, pressure or mechanical tension

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Pathology (AREA)
  • Animal Behavior & Ethology (AREA)
  • Surgery (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Veterinary Medicine (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Orthopedic Medicine & Surgery (AREA)
  • Artificial Intelligence (AREA)
  • Dentistry (AREA)
  • General Engineering & Computer Science (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Physiology (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Physical Education & Sports Medicine (AREA)
  • Transplantation (AREA)
  • Business, Economics & Management (AREA)
  • General Business, Economics & Management (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Vascular Medicine (AREA)
  • Bioinformatics & Computational Biology (AREA)

Abstract

本发明涉及一种膝关节炎减压矫正监测系统，集成了置入式与穿戴式传感器、智能分析模型、云端服务器等组件，旨在实现膝关节炎患者康复过程的精准监测与个性化管理。置入式传感器通过自供电多层结构设计，无创地实时监测膝关节内部压力，而穿戴式传感器则记录患者日常活动中的步态、运动范围与强度。系统利用深度学习算法，从六维度数据中提取特征，构建模型输出健康评分，实现对康复进程的智能评估。云端服务器确保数据安全存储与高效处理，而终端模块为用户提供直观反馈与远程医疗服务。此系统不仅提升了监测精度与患者参与度，还通过个性化康复建议促进了治疗效果，显著优化了膝关节炎的管理流程，为患者康复与生活质量改善带来进步。

The present invention relates to a knee arthritis decompression and correction monitoring system, which integrates components such as implantable and wearable sensors, intelligent analysis models, and cloud servers, aiming to achieve accurate monitoring and personalized management of the rehabilitation process of patients with knee arthritis. The implantable sensor uses a self-powered multi-layer structure design to non-invasively monitor the internal pressure of the knee joint in real time, while the wearable sensor records the patient's gait, range of motion, and intensity during daily activities. The system uses a deep learning algorithm to extract features from six-dimensional data, build a model to output a health score, and achieve intelligent evaluation of the rehabilitation process. The cloud server ensures secure data storage and efficient processing, while the terminal module provides users with intuitive feedback and telemedicine services. This system not only improves monitoring accuracy and patient participation, but also promotes treatment effects through personalized rehabilitation suggestions, significantly optimizes the management process of knee arthritis, and brings progress to patient rehabilitation and quality of life.

Description

Monitoring system is corrected in knee arthritis decompression
Technical Field
The invention relates to the field of medical monitoring, in particular to a knee arthritis decompression correction monitoring system.
Background
Knee arthritis is a common chronic degenerative disease that severely affects the quality of life and exercise ability of patients. Traditional treatment approaches often focus on drug alleviation, physical therapy and later joint replacement surgery, but effective technical support for long-term monitoring of disease conditions and formulation of personalized treatment schemes is lacking. In recent years, with the rapid development of the internet of things, wearable technology and artificial intelligence, real-time monitoring and intelligent evaluation of knee arthritis become possible. Although some wearable devices exist on the market for gait analysis or movement monitoring, there is still a lack of a highly integrated, real-time feedback and intelligent analysis solution for specific needs of knee arthritis patients, especially in terms of pressure distribution during postoperative rehabilitation, accurate assessment of movement function and corrective guidance.
Disclosure of Invention
In order to solve the problems, the invention provides a knee arthritis decompression correction monitoring system, which comprises an embedded sensor, a pulse signal receiving module, a wearable sensor, a monitoring control system, a cloud server, an analysis module and a terminal module;
The embedded sensor is wirelessly connected with the pulse signal receiving module, the pulse signal receiving module is connected with the monitoring control system, and the embedded sensor is arranged in the artificial knee joint after the total knee replacement operation and is used for collecting the pressure of the knee joint of a patient in real time and sending the knee joint pressure collected in real time to the pulse signal receiving module; the pulse signal receiving module sends the acquired data to the monitoring control system;
The wearable sensor is connected with the monitoring control system and is used for collecting movement data in daily activities of a patient, including step frequency, movement range and movement intensity, and sending the collected data to the monitoring control system;
The analysis module is connected with the monitoring control system and is used for inputting the data acquired by the monitoring control system into the monitoring model, and the monitoring model outputs the health score of the patient;
the monitoring control system is connected with the cloud server, the terminal module is connected with the cloud server, the monitoring control system sends the health scores of the patients and various collected data to the cloud server, and the cloud server integrates the data and sends the integrated data to the terminal module for inquiring of the terminal module.
The embedded sensor is arranged in the artificial knee joint after the total knee replacement operation, and is specifically arranged in the tibia platform of the artificial knee joint;
The embedded sensor is arranged in the tibia platform and is respectively positioned at the inner side and the outer side of the tibia platform so as to detect the pressure generated by the medial malleolus and the lateral malleolus on the tibia platform.
The embedded sensor is of a multi-layer structure, adopts a powerless self-powered design and comprises a piezoelectric material layer, an electrode layer, a buffer material layer, an antenna layer, an electric energy temporary storage layer and a flexible circuit board layer from top to bottom;
piezoelectric material layer: the sensor is positioned at the top of the sensor and is made of piezoelectric materials, when the sensor is pressed by external force, the piezoelectric materials deform and generate voltage, the mechanical energy is converted into electric energy, and the physical pressure is directly converted into a measurable electric signal;
Electrode layer: immediately below the piezoelectric material layer, the piezoelectric material layer is made of conductive materials and is used for receiving and transmitting electric signals generated by pressure change;
buffer material layer: the sensor is designed below the electrode layer and is used for absorbing and dispersing uneven pressure or impact applied to the sensor, protecting each layer of the sensor from being damaged, ensuring even pressure transmission and improving the accuracy of measurement and the durability of the sensor;
Antenna layer: the sensor is arranged below the buffer material layer, comprises a micro antenna structure, is connected with the electric energy temporary storage layer and the flexible circuit board layer and is used for transmitting signals generated inside the sensor to the pulse signal receiving module;
The electric energy temporary storage layer: the sensor is positioned between the antenna layer and the flexible circuit board layer and is used for temporarily storing energy collected from the piezoelectric material layer, so that the sensor can work briefly when not pressed;
a flexible circuit board layer: the circuit connection between the layers of the sensor is integrated, so that an electric signal can be transmitted from the electrode layer to the antenna layer, and the sensor comprises a microprocessor, so that the antenna layer can send out a pulse signal like the outside after being extruded, the amplitude of the pulse signal is in direct proportion to the pressure born by the piezoelectric material, and the duration of the pulse signal is the same as the duration of the pressure born by the piezoelectric material.
The pulse signal receiving module is arranged on the intelligent knee pad and is used for receiving the pulse signal transmitted by the embedded sensor in a short distance;
The pulse signal receiving module is internally provided with pulse signal receivers, the number of the pulse signal receivers is the same as that of the embedded sensors, and after a patient wears the intelligent knee pad, the distance between each pulse signal receiver and the corresponding embedded sensor is nearest, so that the signal transmission between a corresponding group of pulse signal receivers and the embedded sensors is strongest.
Wearable sensor integrates in intelligent knee-pad, and wearable sensor is provided with:
The multidimensional motion sensor is internally provided with an accelerometer, a gyroscope and a magnetometer to form a three-dimensional motion capturing system, which can monitor the step frequency and record the motion parameters, the motion range and the intensity of each stage such as sole landing, swing and the like in the gait cycle;
low-power consumption bluetooth communication chip: the wearable sensor is in wireless connection with the monitoring control system through the low-power consumption Bluetooth, so that the instant transmission of data is realized;
the wearable sensor acquires the step frequency S, the movement range R and the movement intensity I of a patient and sends the step frequency S, the movement range R and the movement intensity I to the monitoring control system;
the step frequency S is the number of steps of patient movement in unit time, the movement range R is the angle of knee joint bending of the patient, and the movement intensity I is the movement speed of the patient.
The monitoring control system receives two-way signals from the pulse signal receiving module in real time, wherein the two-way signals respectively correspond to pressure data sent by two embedded sensors arranged on the inner side and the outer side of the tibia platform; decoding and calibrating the received pulse signals, and ensuring the accuracy and consistency of data; integrating the decoded pressure data according to a time sequence to construct a three-dimensional data matrix with pressure changing along with time, wherein each data point not only comprises two pressure values, but also accurately marks a corresponding acquisition time stamp;
The monitoring control system receives the step frequency S, the movement range R and the movement intensity I acquired by the wearable sensor in real time; integrating the acquired data with a three-dimensional data matrix of which the pressure changes along with time to obtain a six-dimensional data matrix; each data point includes a first pressure value F 1, a second pressure value F 2, a step frequency S, a range of motion R, a motion intensity I, and a time T; wherein the first pressure value F 1 corresponds to the pressure of the left ankle and the second pressure value F 2 corresponds to the pressure of the right ankle.
The analysis module adopts a deep learning model to process and score data; the method comprises the following steps:
feature extraction:
for a six-dimensional data matrix, an analysis module firstly performs key feature extraction, wherein the features comprise:
Gait cycle characteristics: analyzing the step frequency S, extracting the duration time, the pace speed and the step length of a gait cycle, and evaluating the stability and the efficiency of the gait;
Pressure dynamic characteristics: extracting pressure peaks, valleys and average values of each step from the three-dimensional pressure time sequence; extracting standard deviation of pressure and pressure change rate in a plurality of steps to reflect the stress condition and the change trend of the knee joint;
Motion capability characteristics: extracting the maximum value and the minimum value of knee joint bending based on the movement range R and the intensity I, and extracting the maximum value, the minimum value and the average value of movement intensity in unit time;
Data processing and model architecture:
the analysis module integrates the extracted feature vectors into a tensor, and the feature vector of each time point comprises pressure features, gait cycle features and movement capability features;
the long-term memory network is adopted as a core, the network structure comprises a plurality of LSTM layers, and each layer is provided with an input gate, a forgetting gate, an output gate and a cell state so as to effectively solve the long-term dependence problem in time sequence data; the LSTM layer is connected with the full connection layer, so that feature learning is deepened, and abstract features of a higher level are extracted; the model predicts a single health score value through a fully connected output layer;
Model training and optimizing:
selecting a mean square error by a loss function, and accurately quantifying the deviation between the predicted health score and the actual score; and (3) carrying out iterative updating of model parameters by using an Adam optimization algorithm, accelerating convergence and improving the generalization capability of the model.
The training method of the model is as follows:
The collection of training data requires patients of different ages, sexes, and health conditions. During acquisition, recording various data in real time in natural walking, specific exercise tasks or daily activities; meanwhile, the health condition of the patient is scored, wherein 0 score indicates that surgery is needed, and 100 score indicates that the patient is completely healthy;
cleaning the original data, removing abnormal values, and carrying out standardization or normalization treatment to ensure that the data can be compared on the same scale; dividing the well-arranged data set into a training set, a verification set and a test set, wherein the proportion of the training set, the verification set and the test set is 70%, 15% and 15%, so that effective training and fair evaluation of a model are ensured;
constructing a feature vector based on the feature extraction method to form structured data suitable for model input;
Adopting a batch gradient descent method, and adjusting LSTM network parameters through back propagation; during the training process, the performance of the model is evaluated on a verification set regularly by using a cross verification strategy, the fitting phenomenon is monitored, and the super-parameters are adjusted according to the requirement;
Optimizing the super parameters by using methods such as grid search or random search based on the performance on the verification set; finally, the generalization capability of the model is evaluated by using the test set, so that the model can be ensured to be not only well fit with training data, but also accurately predict the health scores of the data points which are not seen.
The cloud module implements an efficient data backup strategy and is provided with a recovery mechanism, so that the safety and continuity of all patient data are ensured, services can be quickly recovered even if the system faults or external threats are faced, and the risk of data loss is reduced.
The terminal module provides a highly interactive and personalized user interface, and the display content is customized according to patient preferences or suggestions of medical professionals, including health score trend graphs, key exercise parameter analysis and rehabilitation suggestion reminding, so that visual and easily understood information display is ensured;
the terminal module integrates the video call and instant communication functions, so that a patient can directly carry out remote consultation with a medical expert through the terminal module, share monitoring data and acquire instant feedback and professional guidance;
the terminal module automatically triggers a reminding function according to the health score and the monitoring data output by the analysis module, and the reminding function comprises rehabilitation exercise reminding, abnormal data early warning and periodic review reminding, so that patient compliance is promoted, and a treatment scheme is timely adjusted.
The knee joint inflammation decompression correction monitoring system provided by the invention realizes omnibearing and real-time monitoring of knee joint pressure and motion parameters of a patient through the highly integrated embedded and wearable sensor system. The system not only can accurately capture the pressure change in the knee joint, but also can combine the motion data in daily activities to provide detailed rehabilitation progress information and health scores for doctors, and has the specific beneficial effects that:
the combined application of the two-way embedded sensor and the multidimensional wearable sensor realizes the high-precision monitoring of the stress state and the movement function of the knee joint, is beneficial to finding early abnormalities and provides personalized rehabilitation advice and treatment adjustment for patients.
The embedded sensor adopts a multilayer structure and a self-powered design, and particularly, the innovative application of the piezoelectric material layer ensures that the sensor stably works for a long time under the condition of not depending on an external power supply, reduces the maintenance requirement of embedded equipment, improves the safety and convenience of use of patients, and also reduces the long-term use cost.
The analysis module based on deep learning can accurately evaluate the health condition of a patient by extracting key features and constructing a prediction model, discover problems in the rehabilitation process in time, provide scientific decision support for doctors, and reduce the risk of complications. Through the seamless connection of high in the clouds server and terminal module, the patient can look over self recovered progress and health score through mobile device conveniently, has strengthened patient's self-management consciousness and recovered power.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained from these drawings without inventive faculty for a person skilled in the art.
FIG. 1 is a schematic diagram of the overall architecture of the present invention;
FIG. 2 is a diagram of the mounting position of the embedded sensor of the present invention;
FIG. 3 is a schematic diagram of the structure of the multi-layer sensor of the present invention.
Wherein: 1 piezoelectric material layer, 2 electrode layer, 3 buffer material layer, 4 antenna layer, 5 electric energy temporary storage layer, 6 flexible circuit board layer, 7 shin bone platform, 8 built-in sensor.
Detailed Description
Referring to fig. 1 to 3, the invention provides a knee arthritis decompression correction monitoring system, which comprises an embedded sensor, a pulse signal receiving module, a wearable sensor, a monitoring control system, a cloud server, an analysis module and a terminal module;
The embedded sensor is wirelessly connected with the pulse signal receiving module, the pulse signal receiving module is connected with the monitoring control system, and the embedded sensor is arranged in the artificial knee joint after the total knee replacement operation and is used for collecting the pressure of the knee joint of a patient in real time and sending the knee joint pressure collected in real time to the pulse signal receiving module; the pulse signal receiving module sends the acquired data to the monitoring control system;
The wearable sensor is connected with the monitoring control system and is used for collecting movement data in daily activities of a patient, including step frequency, movement range and movement intensity, and sending the collected data to the monitoring control system;
The analysis module is connected with the monitoring control system and is used for inputting the data acquired by the monitoring control system into the monitoring model, and the monitoring model outputs the health score of the patient;
the monitoring control system is connected with the cloud server, the terminal module is connected with the cloud server, the monitoring control system sends the health scores of the patients and various collected data to the cloud server, and the cloud server integrates the data and sends the integrated data to the terminal module for inquiring of the terminal module.
The embedded sensor 8 is arranged in the artificial knee joint after the total knee replacement operation, and is specifically arranged in the tibia platform 7 of the artificial knee joint;
the embedded sensors 8 are provided in two in the tibial plateau, respectively located on the medial and lateral sides of the tibial plateau 7, to detect the pressure generated by the medial and lateral malleoli on the tibial plateau.
The embedded sensor 8 is of a multi-layer structure, adopts a powerless self-powered design, and comprises a piezoelectric material layer, an electrode layer, a buffer material layer, an antenna layer, an electric energy temporary storage layer and a flexible circuit board layer from top to bottom;
Piezoelectric material layer 1: the sensor is positioned at the top of the sensor and is made of piezoelectric materials, when the sensor is pressed by external force, the piezoelectric materials deform and generate voltage, the mechanical energy is converted into electric energy, and the physical pressure is directly converted into a measurable electric signal;
Electrode layer 2: immediately below the piezoelectric material layer, the piezoelectric material layer is made of conductive materials and is used for receiving and transmitting electric signals generated by pressure change;
buffer material layer 3: the sensor is designed below the electrode layer and is used for absorbing and dispersing uneven pressure or impact applied to the sensor, protecting each layer of the sensor from being damaged, ensuring even pressure transmission and improving the accuracy of measurement and the durability of the sensor;
Antenna layer 4: the sensor is arranged below the buffer material layer, comprises a micro antenna structure, is connected with the electric energy temporary storage layer and the flexible circuit board layer and is used for transmitting signals generated inside the sensor to the pulse signal receiving module;
The electric energy temporary storage layer 5: the sensor is positioned between the antenna layer and the flexible circuit board layer and is used for temporarily storing energy collected from the piezoelectric material layer, so that the sensor can work briefly when not pressed;
Flexible wiring board layer 6: the circuit connection between the layers of the sensor is integrated, so that an electric signal can be transmitted from the electrode layer to the antenna layer, and the sensor comprises a microprocessor, so that the antenna layer can send out a pulse signal like the outside after being extruded, the amplitude of the pulse signal is in direct proportion to the pressure born by the piezoelectric material, and the duration of the pulse signal is the same as the duration of the pressure born by the piezoelectric material.
The pulse signal receiving module is arranged on the intelligent knee pad and is used for receiving the pulse signal transmitted by the embedded sensor in a short distance;
The pulse signal receiving module is internally provided with pulse signal receivers, the number of the pulse signal receivers is the same as that of the embedded sensors, and after a patient wears the intelligent knee pad, the distance between each pulse signal receiver and the corresponding embedded sensor is nearest, so that the signal transmission between a corresponding group of pulse signal receivers and the embedded sensors is strongest.
Wearable sensor integrates in intelligent knee-pad, and wearable sensor is provided with:
The multidimensional motion sensor is internally provided with an accelerometer, a gyroscope and a magnetometer to form a three-dimensional motion capturing system, which can monitor the step frequency and record the motion parameters, the motion range and the intensity of each stage such as sole landing, swing and the like in the gait cycle;
low-power consumption bluetooth communication chip: the wearable sensor is in wireless connection with the monitoring control system through the low-power consumption Bluetooth, so that the instant transmission of data is realized;
the wearable sensor acquires the step frequency S, the movement range R and the movement intensity I of a patient and sends the step frequency S, the movement range R and the movement intensity I to the monitoring control system;
the step frequency S is the number of steps of patient movement in unit time, the movement range R is the angle of knee joint bending of the patient, and the movement intensity I is the movement speed of the patient.
The monitoring control system receives two-way signals from the pulse signal receiving module in real time, wherein the two-way signals respectively correspond to pressure data sent by two embedded sensors arranged on the inner side and the outer side of the tibia platform; decoding and calibrating the received pulse signals, and ensuring the accuracy and consistency of data; integrating the decoded pressure data according to a time sequence to construct a three-dimensional data matrix with pressure changing along with time, wherein each data point not only comprises two pressure values, but also accurately marks a corresponding acquisition time stamp;
The monitoring control system receives the step frequency S, the movement range R and the movement intensity I acquired by the wearable sensor in real time; integrating the acquired data with a three-dimensional data matrix of which the pressure changes along with time to obtain a six-dimensional data matrix; each data point includes a first pressure value F 1, a second pressure value F 2, a step frequency S, a range of motion R, a motion intensity I, and a time T; wherein the first pressure value F 1 corresponds to the pressure of the left ankle and the second pressure value F 2 corresponds to the pressure of the right ankle.
The analysis module adopts a deep learning model to process and score data; the method comprises the following steps:
feature extraction:
for a six-dimensional data matrix, an analysis module firstly performs key feature extraction, wherein the features comprise:
Gait cycle characteristics: analyzing the step frequency S, extracting the duration time, the pace speed and the step length of a gait cycle, and evaluating the stability and the efficiency of the gait;
Pressure dynamic characteristics: extracting pressure peaks, valleys and average values of each step from the three-dimensional pressure time sequence; extracting standard deviation of pressure and pressure change rate in a plurality of steps to reflect the stress condition and the change trend of the knee joint;
Motion capability characteristics: extracting the maximum value and the minimum value of knee joint bending based on the movement range R and the intensity I, and extracting the maximum value, the minimum value and the average value of movement intensity in unit time;
Data processing and model architecture:
the analysis module integrates the extracted feature vectors into a tensor, and the feature vector of each time point comprises pressure features, gait cycle features and movement capability features;
the long-term memory network is adopted as a core, the network structure comprises a plurality of LSTM layers, and each layer is provided with an input gate, a forgetting gate, an output gate and a cell state so as to effectively solve the long-term dependence problem in time sequence data; the LSTM layer is connected with the full connection layer, so that feature learning is deepened, and abstract features of a higher level are extracted; the model predicts a single health score value through a fully connected output layer;
Model training and optimizing:
selecting a mean square error by a loss function, and accurately quantifying the deviation between the predicted health score and the actual score; and (3) carrying out iterative updating of model parameters by using an Adam optimization algorithm, accelerating convergence and improving the generalization capability of the model.
The training method of the model is as follows:
The collection of training data requires patients of different ages, sexes, and health conditions. During acquisition, recording various data in real time in natural walking, specific exercise tasks or daily activities; meanwhile, the health condition of the patient is scored, wherein 0 score indicates that surgery is needed, and 100 score indicates that the patient is completely healthy;
cleaning the original data, removing abnormal values, and carrying out standardization or normalization treatment to ensure that the data can be compared on the same scale; dividing the well-arranged data set into a training set, a verification set and a test set, wherein the proportion of the training set, the verification set and the test set is 70%, 15% and 15%, so that effective training and fair evaluation of a model are ensured;
constructing a feature vector based on the feature extraction method to form structured data suitable for model input;
Adopting a batch gradient descent method, and adjusting LSTM network parameters through back propagation; during the training process, the performance of the model is evaluated on a verification set regularly by using a cross verification strategy, the fitting phenomenon is monitored, and the super-parameters are adjusted according to the requirement;
Optimizing the super parameters by using methods such as grid search or random search based on the performance on the verification set; finally, the generalization capability of the model is evaluated by using the test set, so that the model can be ensured to be not only well fit with training data, but also accurately predict the health scores of the data points which are not seen.
The cloud module implements an efficient data backup strategy and is provided with a recovery mechanism, so that the safety and continuity of all patient data are ensured, services can be quickly recovered even if the system faults or external threats are faced, and the risk of data loss is reduced.
The terminal module provides a highly interactive and personalized user interface, and the display content is customized according to patient preferences or suggestions of medical professionals, including health score trend graphs, key exercise parameter analysis and rehabilitation suggestion reminding, so that visual and easily understood information display is ensured;
the terminal module integrates the video call and instant communication functions, so that a patient can directly carry out remote consultation with a medical expert through the terminal module, share monitoring data and acquire instant feedback and professional guidance;
the terminal module automatically triggers a reminding function according to the health score and the monitoring data output by the analysis module, and the reminding function comprises rehabilitation exercise reminding, abnormal data early warning and periodic review reminding, so that patient compliance is promoted, and a treatment scheme is timely adjusted.
The knee joint inflammation decompression correction monitoring system provided by the invention realizes omnibearing and real-time monitoring of knee joint pressure and motion parameters of a patient through the highly integrated embedded and wearable sensor system. The system not only can accurately capture the pressure change in the knee joint, but also can combine the motion data in daily activities to provide detailed rehabilitation progress information and health scores for doctors, and has the specific beneficial effects that:
the combined application of the two-way embedded sensor and the multidimensional wearable sensor realizes the high-precision monitoring of the stress state and the movement function of the knee joint, is beneficial to finding early abnormalities and provides personalized rehabilitation advice and treatment adjustment for patients.
The embedded sensor adopts a multilayer structure and a self-powered design, and particularly, the innovative application of the piezoelectric material layer ensures that the sensor stably works for a long time under the condition of not depending on an external power supply, reduces the maintenance requirement of embedded equipment, improves the safety and convenience of use of patients, and also reduces the long-term use cost.
The analysis module based on deep learning can accurately evaluate the health condition of a patient by extracting key features and constructing a prediction model, discover problems in the rehabilitation process in time, provide scientific decision support for doctors, and reduce the risk of complications. Through the seamless connection of high in the clouds server and terminal module, the patient can look over self recovered progress and health score through mobile device conveniently, has strengthened patient's self-management consciousness and recovered power.
The description of the foregoing embodiments has been provided for the purposes of illustration and description. It is not intended to be exhaustive or to limit the disclosure. Individual elements or features of a particular embodiment are generally not limited to the particular embodiment, but, where applicable, may be interchanged and used with the selected embodiment even if not specifically shown or described. The same elements or features may also be varied in many ways. Such variations are not to be regarded as a departure from the disclosure, and all such modifications are intended to be included within the scope of the disclosure.
Example embodiments are provided so that this disclosure will be thorough, and will fully convey the scope to those skilled in the art. Numerous details are set forth, such as examples of specific parts, devices, and methods, in order to provide a thorough understanding of embodiments of the present disclosure. It will be apparent to one skilled in the art that the exemplary embodiments may be embodied in many different forms without the use of specific details, and neither should be construed to limit the scope of the disclosure. In certain example embodiments, well-known processes, well-known device structures, and well-known techniques are not described in detail.
The terminology used herein is for the purpose of describing particular example embodiments only and is not intended to be limiting. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. The terms "comprises" and "comprising" are inclusive and, therefore, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. The method steps, processes, and operations described herein are not to be construed as necessarily requiring their performance in the particular order discussed and illustrated, unless specifically indicated. It should also be appreciated that additional or alternative steps may be employed.

Claims (8)

1.一种膝关节炎减压矫正监测系统，包括置入式传感器、脉冲信号接收模块、穿戴式传感器、监测控制系统、云端服务器、分析模块以及终端模块；其特征在于：1. A knee arthritis decompression and correction monitoring system, comprising an implantable sensor, a pulse signal receiving module, a wearable sensor, a monitoring control system, a cloud server, an analysis module and a terminal module; characterized in that: 置入式传感器无线连接脉冲信号接收模块，脉冲信号接收模块连接监测控制系统，置入式传感器设置于全膝置换术后的人工膝关节内，用于实时采集患者的膝关节的压力，并将实时采集的膝关节压力发送给脉冲信号接收模块；脉冲信号接收模块将采集的数据发送给监测控制系统；The implanted sensor is wirelessly connected to the pulse signal receiving module, which is connected to the monitoring and control system. The implanted sensor is arranged in the artificial knee joint after total knee replacement surgery, and is used to collect the pressure of the patient's knee joint in real time, and send the real-time collected knee joint pressure to the pulse signal receiving module; the pulse signal receiving module sends the collected data to the monitoring and control system; 穿戴式传感器连接监测控制系统，用于收集患者日常活动中的运动数据，包括步频、运动范围和运动强度，并将采集的数据发送给监测控制系统；Wearable sensors are connected to the monitoring and control system to collect movement data during the patient's daily activities, including cadence, range of motion, and intensity of movement, and send the collected data to the monitoring and control system; 分析模块连接监测控制系统，用于根据监测控制系统采集的数据输入监测模型，监测模型输出患者的健康评分；The analysis module is connected to the monitoring control system and is used to input the monitoring model according to the data collected by the monitoring control system, and the monitoring model outputs the health score of the patient; 监测控制系统连接云端服务器，终端模块连接云端服务器，监测控制系统将患者的健康评分和采集的各种数据发送至云端服务器，云端服务器将数据整合后发送至终端模块，以备终端模块的查询；The monitoring and control system is connected to the cloud server, and the terminal module is connected to the cloud server. The monitoring and control system sends the patient's health score and various collected data to the cloud server. The cloud server integrates the data and sends it to the terminal module for query by the terminal module. 置入式传感器设置于全膝置换术后的人工膝关节内，具体的置于人工膝关节的胫骨平台内；The implantable sensor is placed in the artificial knee joint after total knee replacement, specifically in the tibial plateau of the artificial knee joint; 置入式传感器在胫骨平台内设置有两个，分别位于胫骨平台的内侧和外侧，以检测内踝和外踝对胫骨平台产生的压力；Two implantable sensors are arranged in the tibial plateau, one on the inner side and the other on the outer side of the tibial plateau, to detect the pressure exerted by the inner and outer ankles on the tibial plateau; 置入式传感器为多层结构，采用无电源自供电设计，从上至下包括压电材料层、电极层、缓冲材料层、天线层、电能暂存层、柔性线路板层；The embedded sensor is a multi-layer structure, adopting a power-free self-powered design, which includes a piezoelectric material layer, an electrode layer, a buffer material layer, an antenna layer, a power storage layer, and a flexible circuit board layer from top to bottom; 压电材料层：位于传感器顶部，采用压电材料制成，当受到外力压迫时，压电材料会发生形变并产生电压，将机械能转换为电能，直接将物理压力转变为可测量的电信号；Piezoelectric material layer: Located on the top of the sensor, it is made of piezoelectric material. When subjected to external pressure, the piezoelectric material will deform and generate voltage, converting mechanical energy into electrical energy, directly converting physical pressure into a measurable electrical signal; 电极层：紧邻压电材料层下方，由导电材料构成，用于接收并传递压力变化产生的电信号；Electrode layer: It is located just below the piezoelectric material layer and is made of conductive material. It is used to receive and transmit electrical signals generated by pressure changes. 缓冲材料层：设计于电极层之下，用于吸收并分散施加在传感器上的不均匀压力或冲击，保护传感器各层不受损伤，同时确保压力传递均匀，提高测量的准确性和传感器的耐用性；Buffer material layer: designed under the electrode layer, used to absorb and disperse the uneven pressure or impact applied to the sensor, protect the sensor layers from damage, and ensure uniform pressure transmission, thereby improving the measurement accuracy and durability of the sensor; 天线层：设置于缓冲材料层下方，包含一个微型天线结构与电能暂存层和柔性线路板层相连，用于将传感器内部产生的信号传输到脉冲信号接收模块；电能暂存层：位于天线层和柔性线路板层之间，用于临时存储从压电材料层收集能量，确保传感器在不受压时还能短暂工作；Antenna layer: It is arranged below the buffer material layer, and includes a micro-antenna structure connected to the power temporary storage layer and the flexible circuit board layer, and is used to transmit the signal generated inside the sensor to the pulse signal receiving module; Power temporary storage layer: It is located between the antenna layer and the flexible circuit board layer, and is used to temporarily store the energy collected from the piezoelectric material layer, so as to ensure that the sensor can work briefly when it is not under pressure; 柔性线路板层：集成了传感器各层之间的电路连接，使得电信号能从电极层传递到天线层，并包含微处理器，使得压电材料层在受到挤压之后，天线层能够像外界发出脉冲信号，脉冲信号的振幅和压电材料承受的压力大小成正比，脉冲信号的持续时间与压电材料承受压力的持续时间相同。Flexible circuit board layer: Integrates the circuit connections between the various layers of the sensor, allowing electrical signals to be transmitted from the electrode layer to the antenna layer, and contains a microprocessor so that after the piezoelectric material layer is squeezed, the antenna layer can send a pulse signal to the outside world. The amplitude of the pulse signal is proportional to the pressure on the piezoelectric material, and the duration of the pulse signal is the same as the duration of the pressure on the piezoelectric material. 2.根据权利要求1所述的一种膝关节炎减压矫正监测系统，其特征在于：脉冲信号接收模块设置在智能护膝上，用于近距离接收置入式传感器发射的脉冲信号；2. A knee arthritis decompression correction monitoring system according to claim 1, characterized in that: a pulse signal receiving module is arranged on the intelligent knee pad, and is used to receive the pulse signal emitted by the embedded sensor at a close distance; 脉冲信号接收模块内设置脉冲信号接收器，脉冲信号接收器的数量与置入式传感器的数量相同，且当患者穿上智能护膝后，每个脉冲信号接收器与其对应的置入式传感器的距离最近，从而保证对应的一组脉冲信号接收器与置入式传感器的信号传输最强。Pulse signal receivers are arranged in the pulse signal receiving module. The number of pulse signal receivers is the same as the number of implanted sensors. When the patient wears the smart knee brace, the distance between each pulse signal receiver and its corresponding implanted sensor is the shortest, thereby ensuring that the signal transmission between a corresponding group of pulse signal receivers and the implanted sensors is the strongest. 3.根据权利要求2所述的一种膝关节炎减压矫正监测系统，其特征在于：穿戴式传感器集成于智能护膝内，穿戴式传感器设置有：3. A knee arthritis decompression correction monitoring system according to claim 2, characterized in that: the wearable sensor is integrated into the smart knee brace, and the wearable sensor is provided with: 多维度运动传感器，内置加速度计、陀螺仪与磁力计，形成三维运动捕捉系统，能够监测步频，记录步态周期中的脚掌着地、摆动各个阶段的运动参数，以及运动范围和强度；Multi-dimensional motion sensor, with built-in accelerometer, gyroscope and magnetometer, forms a three-dimensional motion capture system that can monitor cadence and record motion parameters of the foot landing and swinging stages in the gait cycle, as well as the range and intensity of motion; 低功耗蓝牙通信芯片：穿戴式传感器通过低功耗蓝牙与监测控制系统无线连接，实现数据的即时传输；Low-power Bluetooth communication chip: Wearable sensors are wirelessly connected to the monitoring and control system via low-power Bluetooth to achieve instant data transmission; 穿戴式传感器采集患者步频S、运动范围R、运动强度I，并将其发送至监测控制系统；Wearable sensors collect the patient's cadence S, range of motion R, and exercise intensity I, and send them to the monitoring and control system; 步频S为单位时间内患者移动的步数，运动范围R患者膝关节弯曲的角度，运动强度I为患者的移动速度。The step frequency S is the number of steps the patient moves per unit time, the range of motion R is the angle of the patient's knee joint bending, and the exercise intensity I is the patient's movement speed. 4.根据权利要求3所述的一种膝关节炎减压矫正监测系统，其特征在于：监测控制系统实时接收来自脉冲信号接收模块的双路信号，双路信号分别对应于设置在胫骨平台内侧和外侧的两个置入式传感器所发送的压力数据；对接收到的脉冲信号进行解码与校准，确保数据的准确性与一致性；将解码后的压力数据按照时间序列进行整合，构建压力随时间变化的三维数据矩阵，每一数据点不仅包含两个压力值，还精确标记了相应的采集时间戳；4. A knee arthritis decompression and correction monitoring system according to claim 3, characterized in that: the monitoring and control system receives a dual-channel signal from a pulse signal receiving module in real time, the dual-channel signal corresponding to the pressure data sent by two implanted sensors arranged on the inner and outer sides of the tibial plateau; the received pulse signal is decoded and calibrated to ensure the accuracy and consistency of the data; the decoded pressure data is integrated according to the time series to construct a three-dimensional data matrix of pressure changes over time, and each data point not only contains two pressure values, but also accurately marks the corresponding acquisition timestamp; 监测控制系统实时接收穿戴式传感器采集的步频S、运动范围R、运动强度I；将采集的数据与压力随时间变化的三维数据矩阵整合，得到六维度数据矩阵；每一数据点包括第一压力值F1，第二压力值F2、步频S、运动范围R、运动强度I以及时间T；其中第一压力值F1对应左踝的压力，第二压力值F2对应右踝的压力。The monitoring and control system receives the step frequency S, movement range R, and exercise intensity I collected by the wearable sensor in real time; integrates the collected data with the three-dimensional data matrix of pressure changes over time to obtain a six-dimensional data matrix; each data point includes a first pressure value F1 , a second pressure value F2 , step frequency S, movement range R, exercise intensity I and time T; the first pressure value F1 corresponds to the pressure of the left ankle, and the second pressure value F2 corresponds to the pressure of the right ankle. 5.根据权利要求4所述的一种膝关节炎减压矫正监测系统，其特征在于：分析模块采用深度学习模型进行数据处理与评分；具体如下：5. A knee arthritis decompression correction monitoring system according to claim 4, characterized in that: the analysis module uses a deep learning model for data processing and scoring; specifically as follows: 特征提取：Feature extraction: 针对六维度数据矩阵，分析模块首先进行关键特征提取，特征包括：For the six-dimensional data matrix, the analysis module first extracts key features, including: 步态周期特征：分析步频S，提取步态周期的持续时间、步速、步长，评估步态的稳定性和效率；Gait cycle characteristics: Analyze the step frequency S, extract the duration, speed, and step length of the gait cycle, and evaluate the stability and efficiency of the gait; 压力动态特征：从三维压力时间序列中提取每一步的压力峰值、谷值、平均值；提取多个步中压力的标准差以及压力变化率，以反映膝关节受力情况及其变化趋势；Pressure dynamic characteristics: Extract the peak value, valley value and average value of pressure in each step from the three-dimensional pressure time series; extract the standard deviation of pressure and pressure change rate in multiple steps to reflect the force condition of the knee joint and its changing trend; 运动能力特征：基于运动范围R和强度I，提取膝关节弯曲的最大值、最小值，提取单位时间运动强度的最大值、最小值和平均值；Sports ability characteristics: Based on the range of motion R and intensity I, the maximum and minimum values of knee flexion, and the maximum, minimum and average values of the exercise intensity per unit time are extracted; 数据处理与模型架构：Data processing and model architecture: 分析模块将提取的特征向量整合为一个张量，每个时间点的特征向量包含压力特征、步态周期特征、运动能力特征；The analysis module integrates the extracted feature vectors into a tensor. The feature vector at each time point contains pressure features, gait cycle features, and movement ability features. 采用长短期记忆网络为核心，网络结构包括多个LSTM层，每层配备输入门、遗忘门、输出门和细胞状态，以有效处理时间序列数据中的长期依赖问题；LSTM层之后接续全连接层，以深化特征学习并提取更高层次的抽象特征；模型最终通过一个全连接输出层预测单一的健康评分值；The long short-term memory network is used as the core. The network structure includes multiple LSTM layers, each of which is equipped with input gates, forget gates, output gates, and cell states to effectively handle long-term dependency problems in time series data. The LSTM layer is followed by a fully connected layer to deepen feature learning and extract higher-level abstract features. The model finally predicts a single health score value through a fully connected output layer. 模型训练与优化：Model training and optimization: 损失函数选取均方误差，精确量化预测健康评分与实际评分的偏差；使用Adam优化算法进行模型参数的迭代更新，加速收敛并提高模型泛化能力。The loss function selects the mean square error to accurately quantify the deviation between the predicted health score and the actual score; the Adam optimization algorithm is used to iteratively update the model parameters to accelerate convergence and improve the generalization ability of the model. 6.根据权利要求5所述的一种膝关节炎减压矫正监测系统，其特征在于：模型的训练方法如下：6. A knee arthritis decompression correction monitoring system according to claim 5, characterized in that: the training method of the model is as follows: 训练数据的收集要求包括不同年龄、性别、健康状况的患者；采集时，在自然行走、特定运动任务或日常活动中实时记录各项数据；同时对患者健康状况进行评分，0分表示需要手术，100分表示完全健康；The training data collection requirements include patients of different ages, genders, and health conditions. During the collection, various data are recorded in real time during natural walking, specific sports tasks or daily activities. At the same time, the patient's health status is scored, with 0 points indicating the need for surgery and 100 points indicating complete health. 对原始数据进行清洗，剔除异常值，标准化或归一化处理，确保数据在同一尺度上可比较；将整理好的数据集划分为训练集、验证集和测试集，比例为70％、15％、15％，以保证模型的有效训练与公正评估；Clean the raw data, remove outliers, and standardize or normalize them to ensure that the data are comparable on the same scale; divide the sorted data set into training set, validation set, and test set with a ratio of 70%, 15%, and 15% to ensure effective training and fair evaluation of the model; 基于所述的特征提取方法，构建特征向量，形成适合模型输入的结构化数据；采用分批梯度下降法，通过反向传播调整LSTM网络参数；在训练过程中，使用交叉验证策略定期在验证集上评估模型性能，监控过拟合现象，并根据需要调整超参数；Based on the feature extraction method, construct feature vectors to form structured data suitable for model input; use batch gradient descent method to adjust LSTM network parameters through back propagation; during the training process, use cross-validation strategy to regularly evaluate model performance on the validation set, monitor overfitting, and adjust hyperparameters as needed; 基于验证集上的表现，通过网格搜索或随机搜索方法优化超参数；最终，利用测试集评估模型的泛化能力，确保模型不仅能很好地拟合训练数据，也能准确预测未见过的数据点的健康评分。Based on the performance on the validation set, the hyperparameters are optimized through grid search or random search methods; finally, the generalization ability of the model is evaluated using the test set to ensure that the model can not only fit the training data well, but also accurately predict the health scores of unseen data points. 7.根据权利要求1所述的一种膝关节炎减压矫正监测系统，其特征在于：云端模块实施高效的数据备份策略，并配备恢复机制，确保所有患者数据的安全性与连续性，即使面临系统故障或外部威胁，也能迅速恢复服务，减少数据丢失风险。7. A knee arthritis decompression and correction monitoring system according to claim 1, characterized in that: the cloud module implements an efficient data backup strategy and is equipped with a recovery mechanism to ensure the security and continuity of all patient data. Even in the face of system failure or external threats, the service can be quickly restored to reduce the risk of data loss. 8.根据权利要求1所述的一种膝关节炎减压矫正监测系统，其特征在于：终端模块提供高度互动与个性化的用户界面，根据患者偏好或医疗专业人士的建议，定制显示内容，包括健康评分趋势图、关键运动参数分析、康复建议提醒，确保信息展示直观易懂；8. A knee arthritis decompression and correction monitoring system according to claim 1, characterized in that: the terminal module provides a highly interactive and personalized user interface, and customizes the display content according to the patient's preferences or the advice of medical professionals, including health score trend charts, key sports parameter analysis, and rehabilitation advice reminders, to ensure that the information display is intuitive and easy to understand; 终端模块集成视频通话与即时通讯功能，使患者能够直接通过终端模块与医疗专家进行远程咨询，分享监测数据，获取即时反馈与专业指导；The terminal module integrates video calling and instant messaging functions, allowing patients to directly consult with medical experts through the terminal module, share monitoring data, and obtain instant feedback and professional guidance; 终端模块根据分析模块输出的健康评分与监测数据，终端模块自动触发提醒The terminal module automatically triggers reminders based on the health scores and monitoring data output by the analysis module 功能，包括康复锻炼提醒、异常数据预警、定期复查提示，促进患者依从性，Functions include rehabilitation exercise reminders, abnormal data warnings, and regular review reminders to promote patient compliance. 及时调整治疗方案。Adjust treatment plan in time.
CN202410550155.6A 2024-05-06 2024-05-06 A knee arthritis decompression correction monitoring system Active CN118592960B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410550155.6A CN118592960B (en) 2024-05-06 2024-05-06 A knee arthritis decompression correction monitoring system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410550155.6A CN118592960B (en) 2024-05-06 2024-05-06 A knee arthritis decompression correction monitoring system

Publications (2)

Publication Number Publication Date
CN118592960A CN118592960A (en) 2024-09-06
CN118592960B true CN118592960B (en) 2024-11-22

Family

ID=92559798

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410550155.6A Active CN118592960B (en) 2024-05-06 2024-05-06 A knee arthritis decompression correction monitoring system

Country Status (1)

Country Link
CN (1) CN118592960B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119405267A (en) * 2024-10-18 2025-02-11 深圳市眼科医院(深圳市眼病防治研究所) An intelligent device for postoperative body position monitoring in ophthalmology
CN118975799B (en) * 2024-10-21 2024-12-31 悟通感控(北京)科技有限公司 Knee joint pressure sensing device and system
CN119385507A (en) * 2024-10-22 2025-02-07 北京安颂科技有限公司 Optical fiber sensing system and method for online monitoring in human knee replacement surgery

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5438705B2 (en) * 2011-02-28 2014-03-12 東芝テック株式会社 Head pressure adjusting device, image forming apparatus, and head pressure adjusting method
DK3013283T3 (en) * 2013-06-23 2021-03-08 Canary Medical Inc Devices, systems and methods for monitoring knee replacements
CN106175774A (en) * 2016-07-07 2016-12-07 清华大学 A kind of novel knee joint/hip replacement postoperative rehabilitation walking monitoring system
KR102495522B1 (en) * 2021-03-26 2023-02-06 한국과학기술원 Pulse sensing module and system for calculating blood pressure using the same
CN113171084A (en) * 2021-05-06 2021-07-27 金华至和网络科技有限公司 Intelligent orthopedic joint rehabilitation monitoring system and monitoring method
CN117898679A (en) * 2024-02-27 2024-04-19 北京大学 Wireless passive knee joint compartment pressure measurement system implanted for long time

Also Published As

Publication number Publication date
CN118592960A (en) 2024-09-06

Similar Documents

Publication Publication Date Title
CN118592960B (en) A knee arthritis decompression correction monitoring system
US20230022710A1 (en) Systems and methods for processing and analyzing kinematic data from intelligent kinematic devices
CN115486837B (en) Gait analysis method, gait analysis system and device for improving walking disorder
CN106267694B (en) Fracture of lower limb rehabilitation system and its control method
US20220409098A1 (en) A wearable device for determining motion and/or a physiological state of a wearer
CN102697507B (en) System for analyzing walking state of rehabilitation training of patient
US20220313119A1 (en) Artificial intelligence-based shoulder activity monitoring system
US20260060572A1 (en) Methods, systems, and computer readable media for detecting and monitoring gait using a portable gait biofeedback system
CN119896473A (en) A gait detection and abnormality recognition system based on multi-sensor fusion
Shefa et al. IoT-based smart ankle-foot orthosis for patients with gait imbalance
US20220409125A1 (en) Bio-signal acquisition and feedback
CN111063163A (en) Postoperative monitoring system for lower limb fracture
CN119226756A (en) An effect evaluation system for children's lower limb rehabilitation training
Hou et al. A Fully Self‐Powered Digital Wearable System for the Auxiliary Treatment of Plantar Fasciitis
Pai et al. Development of smart sole based foot ulcer prediction system
CN115458122A (en) Rehabilitation exercise model based on BP neural network
CN115349853A (en) Intelligent recognition method and system for human lower limb rehabilitation training
CN113951872A (en) Pressure monitoring system for rehabilitation exercise after lower limb fracture and using method
Qin et al. Application progress and future prospects of smart wearable devices in postoperative rehabilitation of lower limb fractures: A mini review
Sathe et al. Pre-habilitation and wellness through gait analysis using body worn sensors
Arunagiri Gait analysis system using smart insoles to improve sports performance
US20250375229A1 (en) Smart Trauma System
CN119993364B (en) A plantar pressure collection method and system for weight-bearing rehabilitation
CN121768674A (en) Basketball player sports injury risk prediction and rehabilitation training planning system
US20240335138A1 (en) Iot-based podiatric activity tracking and recommendation system

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