Remote diagnosis, treatment and rehabilitation system for knee osteoarthritis

Abstract

The invention discloses a remote diagnosis and treatment rehabilitation system for knee osteoarthritis, relates to the technical field of arthritis rehabilitation treatment systems, and aims to solve the problems of single data acquisition, difficulty in quantification of rehabilitation effects, lack of individuation of training schemes and insufficient action correction in the prior art. The system comprises an intelligent knee joint monitoring device, a data analysis module, a personalized rehabilitation scheme generation module, a remote communication module and a rehabilitation training guidance module. The intelligent knee joint monitoring device can collect multi-dimensional data such as knee joint movement angle, instantaneous load pressure and acceleration; the data analysis module calculates key indexes such as knee joint activity range, total load and rehabilitation index through an algorithm; the personalized rehabilitation scheme generation module dynamically adjusts training intensity and load based on an analysis result; the rehabilitation training guidance module can detect action deviation in real time and provide correction feedback; and the remote communication module realizes data interaction and diagnosis and treatment optimization between the patient and the doctor. And a closed-loop remote rehabilitation management process is adopted.

Description

Technical Field

[0001] The present invention relates to the technical field of arthritis rehabilitation treatment systems, and particularly to a remote diagnosis and treatment rehabilitation system for knee osteoarthritis. Background Art

[0002] Knee osteoarthritis is a common chronic degenerative joint disease, especially with a relatively high incidence in the middle-aged and elderly population. Its main manifestations are joint pain, stiffness, and limited mobility. This disease seriously affects the quality of life of patients and is one of the main causes of global disability.

[0003] Currently, the treatment methods for knee osteoarthritis include drug treatment, physical therapy (such as electrotherapy, heat therapy, etc.), injection therapy (such as hyaluronic acid injection), and surgical treatment (such as joint replacement).

[0004] In early and middle-stage patients, rehabilitation training (such as knee flexion and extension activities, muscle strengthening training, etc.) is considered one of the most effective non-surgical treatment methods. This method relieves the pain of patients and delays the progression of the disease by improving joint mobility and strengthening muscles.

[0005] Deficiencies of traditional rehabilitation training: Dependence on professional guidance: Patients usually need to receive training under the guidance of a physiotherapist in a rehabilitation center. This not only increases the travel burden on patients but also limits the time and frequency of rehabilitation.

[0006] Lack of real-time monitoring: In home rehabilitation training, it is difficult to professionally monitor the training movements, training intensity, and joint load of patients, resulting in unsatisfactory training effects and even possible exacerbation of the condition.

[0007] Difficult-to-quantify rehabilitation effects: In the existing technology, the rehabilitation effects usually rely on the subjective evaluation of physiotherapists, lacking scientific and quantitative indicators to dynamically track and evaluate the rehabilitation progress of patients.

[0008] With the development of intelligent devices and remote medical technologies, some preliminary remote rehabilitation systems have been introduced into the rehabilitation training of knee osteoarthritis. These systems mainly collect the basic movement data of patients through wearable devices and remotely send reports to doctors.

[0009] However, these systems generally have the following deficiencies: Incomplete data collection: They can only collect the basic movement angles of patients (such as joint mobility), lacking the monitoring of multi-dimensional data such as joint force, movement trajectory, and acceleration.

[0010] Insufficient personalized guidance: Most systems adopt preset training programs and are difficult to dynamically adjust the training load and intensity according to the real-time status of patients.

[0011] Limited real-time interaction capabilities: The system often serves only as a data collection tool and cannot detect deviations in the patient's movements in real time during training and provide corrective feedback.

[0012] Insufficient quantification of rehabilitation effects: It is difficult to quantify the rehabilitation effects through scientific algorithms and objective indicators, and the patient's rehabilitation progress lacks intuitive data support.

[0013] The deficiencies of the existing technologies in the rehabilitation training of knee osteoarthritis are mainly reflected in the following aspects:

[0014] Incomplete data collection, unable to monitor the movement angle, force condition, and dynamic load of the knee joint in real time.

[0015] Lack of personalized rehabilitation plan generation function, insufficient adjustment of training intensity and load, and uneven training effects among patients.

[0016] Unable to detect deviations in the patient's movements in real time, resulting in incorrect movements not being corrected, which may cause secondary damage to the joint.

[0017] The evaluation method of rehabilitation effects lacks scientificity and dataization, and patients and doctors cannot accurately understand the rehabilitation progress.

[0018] Lack of a complete closed-loop management process, and it is difficult for the patient's training data and the doctor's feedback to form a dynamic linkage.

[0019] Therefore, we designed a remote diagnosis and treatment rehabilitation system for knee osteoarthritis to solve the above problems. Summary of the Invention

[0020] On the one hand, the present invention proposes a remote diagnosis and treatment rehabilitation system for knee osteoarthritis, which includes:

[0021] Intelligent knee joint monitoring device: used to collect knee joint movement data, including knee joint movement angle θ(t), load pressure P(t), and movement acceleration a(t);

[0022] Data analysis module: calculates the knee joint movement range R, total joint load L, rehabilitation index CI, and movement deviation E through formulas;

[0023] Personalized rehabilitation plan generation module: generates a dynamically adjusted personalized rehabilitation training plan according to the rehabilitation index CI and training intensity I calculated by the data analysis module;

[0024] Remote communication module: used for data transmission, diagnosis and treatment interaction, and training feedback between patients and doctors;

[0025] Rehabilitation training guidance module: used to guide the patient to complete the training movements in real time and correct the patient's training process according to the movement deviation.

[0026] On the other hand, the motion data collected by the intelligent knee joint monitoring device includes: the knee joint movement angle θ(t), with a range of 0° ≤ θ(t) ≤ 180°;

[0027] The instantaneous load pressure P(t), with the unit of N;

[0028] The instantaneous acceleration a(t), with the unit of m / s 2 , satisfying the following derivation relationship:

[0029]

[0030] where is the angular velocity and x(t) is the knee joint displacement.

[0031] On the other hand, the data analysis module calculates the knee joint movement range R, the total joint load L, and the rehabilitation index CI through the following formulas. Among them, the knee joint movement range R:

[0032]

[0033] where the unit of R is radian and [t1, t2] is the acquisition time period;

[0034] The total joint load L:

[0035]

[0036] where the unit of L is N·m / s 2 , indicating the total load borne by the joint;

[0037] The rehabilitation index CI:

[0038]

[0039] where CI is a dimensionless index, R baseline , L baseline is the initial state of the patient, R current , L current is the current training state.

[0040] On the other hand, the dynamic change trend of the rehabilitation index CI is predicted through the following formula: Rehabilitation index time change formula:

[0041]

[0042] where T is the training cycle time, R baseline , L baseline is the initial state of the patient, R current , L current is the current training state;

[0043] Predict the next round of rehabilitation index CI t+1 :

[0044]

[0045] Among them, α is a regulation factor, and the range is 0.1 ≤ α ≤ 0.5.

[0046] On the other hand, the personalized rehabilitation plan generation module dynamically adjusts the training load of the patient based on the rehabilitation index CI and the training intensity I:

[0047] Calculation formula of training intensity:

[0048] I = k1·R + k2·L

[0049] Among them, k1 and k2 are weight factors, and k1 + k2 = 1;

[0050] Calculation formula for adjusting training load:

[0051] F = β·I + γ·(CI target -CI current )

[0052] Among them, β and γ are regulation factors, and the ranges are β ≥ 0.1 and γ ≤ 1.0.

[0053] On the other hand, the rehabilitation training guidance module detects the deviation of the patient's movement through the following formula:

[0054]

[0055] Among them, the unit of E is degree, representing the total amount of movement deviation, n is the number of movement sampling points, θ actual,i is the actual angle, and θ ideal,i is the target angle.

[0056] On the other hand, when the movement deviation E > E threshold , the system adjusts the training intensity through the following formula:

[0057]

[0058] Among them, E threshold is the movement deviation threshold, and the range is 5° ≤ E threshold ≤ 20°. On the other hand, the remote communication module supports data encryption and adopts the following encryption formula:

[0059] C = Enc(K, D)

[0060] Among them, C is the encrypted data, K is the key, and D is the original data.

[0061] On the other hand, the system calculates the overall change rate of the training effect through the following formula:

[0062]

[0063] where ΔCI is the change rate of the rehabilitation effect, and CI final is the final rehabilitation index (dimensionless), representing the rehabilitation status of the patient at the end of the training in the current stage, and CI initial is the initial rehabilitation index (dimensionless), representing the rehabilitation status of the patient at the start of the training in the current stage.

[0064] On the other hand, the system optimizes the rehabilitation plan through the following formula:

[0065]

[0066] where CI optimal is the optimized rehabilitation index, used for adjusting the next round of training plan, and R baseline , L baseline is the initial state of the patient, and R current , L current is the current training state.

[0067] Compared with the prior art, the present invention has the following beneficial effects:

[0068] 1. The remote diagnosis, treatment and rehabilitation system for knee osteoarthritis of the present invention comprehensively collects multi-dimensional data of the knee joint through an intelligent knee joint monitoring device, including the movement angle, joint force and acceleration, and can accurately reflect the movement state of the knee joint. Combined with the data analysis module, the system uses scientific quantitative indicators such as the rehabilitation index (CI) to dynamically track the rehabilitation progress of the patient, solves the problems of single data collection and non-quantifiable rehabilitation effect in the prior art, and provides a reliable basis for scientific evaluation.

[0069] 2. The system of the present invention comprehensively evaluates the rehabilitation status of the patient through an algorithm, generates a personalized training plan according to real-time data, and dynamically adjusts the training intensity and load according to the training effect and the patient's state, ensuring the scientificity and safety of the rehabilitation training. Compared with traditional rehabilitation methods, the present invention avoids the limitations of a single preset plan, can better meet the actual needs of different patients, and improves the efficiency and effect of rehabilitation training.

[0070] 3. The system of the present invention has the function of real-time detecting the deviation of the patient's training actions, can give timely feedback and prompt correction when the patient's actions are incorrect, and effectively prevents secondary injuries caused by incorrect actions. In addition, the system realizes the closed-loop management of patient data collection, analysis and feedback, doctor guidance, and plan optimization, which can not only reduce the rehabilitation burden of the patient, but also enhance the doctor's remote control ability over the patient's rehabilitation, and comprehensively improve the rehabilitation quality and experience. Brief Description of the Drawings

[0071] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0072] Figure 1 It is a system block diagram of a remote diagnosis, treatment and rehabilitation system for knee osteoarthritis; Detailed Embodiments

[0073] In order to make the objectives, technical solutions and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention with reference to the drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

[0074] The following will describe in detail the specific embodiments of the present invention with reference to the attached Figure 1 drawings.

[0075] A remote diagnosis, treatment and rehabilitation system for knee osteoarthritis provided by the embodiment of the present invention, the core modules of the system include:

[0076] Intelligent knee joint monitoring device: used to collect key motion data of the knee joint, including angle θ(t), pressure P(t) and acceleration a(t).

[0077] Data analysis module: calculate the knee joint range of motion R, total joint load L, rehabilitation index CI and motion deviation E based on the collected data, and dynamically evaluate the patient's rehabilitation progress.

[0078] Personalized rehabilitation plan generation module: generate a dynamically adjusted training plan based on the data analysis results, including training intensity I and training load F.

[0079] Remote communication module: used for data transmission, diagnosis and treatment interaction and feedback optimization between patients and doctors.

[0080] Rehabilitation training guidance module: used to guide patients to complete training actions and correct motion deviations during the training process through real-time monitoring.

[0081] Device structure: The intelligent knee joint monitoring device is a wearable device, which consists of the following parts: Angle sensor: used to collect the knee joint movement angle θ(t) and angular velocity For example, a rotary encoder or an optical angle sensor. Pressure sensor: used to measure the load pressure P(t) on the knee joint, such as a flexible film pressure sensor or a strain gauge sensor. Acceleration sensor: used to detect the motion acceleration a(t) of the knee joint, such as a triaxial accelerometer or an inertial measurement unit (IMU).

[0082] Data acquisition and transmission module: transmits data to other modules of the system via low-power Bluetooth or Wi-Fi.

[0083] Housing and accessories: designed with a flexible material or a 3D printed housing to ensure the comfort and stability of the device.

[0084] Data acquisition process: The device is installed on the patient's knee joint, and the accuracy of the data is ensured through calibration. The angle sensor records the flexion and extension angle θ(t) and angular velocity of the knee joint in real time The pressure sensor records the instantaneous load pressure P(t) on the knee joint. The acceleration sensor detects the acceleration a(t) of the knee joint movement and calculates the load energy of the joint in combination with the pressure data.

[0085] Data transmission and storage: All data collected by the sensors is transmitted to the data analysis module in real time via the Bluetooth or Wi-Fi module, and is stored locally and in the cloud at the same time to ensure the security and continuity of the data.

[0086] Calculation of the knee joint range of motion R: The knee joint range of motion R is used to evaluate joint flexibility:

[0087]

[0088] θ(t): the angle of the knee joint at time t (unit: radian, 0° ≤ θ(t) ≤ 180°). Knee joint angular velocity, [t1, t2]: the acquisition time range.

[0089] Implementation: The angle sensor collects θ(t) in real time and calculates its change rate to obtain the joint range of motion.

[0090] Calculation of the total joint load L: The total joint load L evaluates the pressure load during the knee joint movement:

[0091]

[0092] P(t): instantaneous joint pressure (unit: N), a(t): joint acceleration, x(t): the movement trajectory of the joint.

[0093] Implementation: Collect data in real time through the pressure sensor and accelerometer and calculate.

[0094] Calculation of the Rehabilitation Index CI: The rehabilitation index CI is used to evaluate the patient's rehabilitation progress:

[0095]

[0096] R baseline ,L baseline : Range of motion and total load in the initial state, R current ,L current : Range of motion and total load in the current state.

[0097] Implementation: Quantify the rehabilitation effect by comparing current and baseline data.

[0098] Calculation of the Motion Deviation E: The motion deviation E is used to monitor the accuracy of training actions:

[0099]

[0100] θ actual,i : The actual angle of the patient's i-th motion; θ ideal,i : The target angle of the standard motion.

[0101] Implementation: Collect data on actual and target motions in real time and calculate the total deviation.

[0102] Calculation of the Training Intensity I and Load F: Training intensity I: I = k1·R + k2·L

[0103] Training load F: F = β·I + γ·(CI target -CI current )

[0104] k1, k2 are weight factors, and β, γ are adjustment factors.

[0105] Example 1: Initial rehabilitation assessment and training plan formulation;

[0106] Patient Ms. Wang (65 years old) received rehabilitation treatment for knee osteoarthritis for the first time, and the doctor formulated an initial rehabilitation training plan for her. The patient wore a smart knee joint monitoring device in the rehabilitation center and completed basic knee joint flexion and extension training, and the system evaluated the function of her knee joint.

[0107] Data collection: The patient completed two sets of knee joint flexion and extension training (10 times per set):

[0108] Angle data: The angle sensor recorded the range of motion of the knee joint [0°, 45°, 90°, 45°, 0°].

[0109] Load pressure data: The pressure sensor recorded the instantaneous load of the knee joint [150, 200, 300, 200, 150] N.

[0110] Acceleration data: The acceleration sensor records the acceleration [0, 0.4, 1.0, 0.4, 0] m / s 2 .

[0111] Range of motion of the knee joint R: The angular velocity data is calculated through Calculation:

[0112]

[0113] Range of motion:

[0114] Total joint load L: The instantaneous load pressure and acceleration data are used to calculate the joint load:

[0115]

[0116] Rehabilitation index CI:

[0117] Initial state:

[0118] R baseline = 2.5 rad, L baseline = 300 N·pm / s 2

[0119] Calculation of the rehabilitation index:

[0120]

[0121] Training intensity I: Weighting factors k1 = 0.6, k2 = 0.4:

[0122] I = k1·R + k2·L = 0.6·2.0 + 0.4·240 = 96.8

[0123] Training load F: Target rehabilitation index CI target = 1.2, Adjustment factor β = 0.5, γ = 0.5:

[0124] F = β·I + γ·(CI target - CI current ) = 0.5·96.8 + 0.5·(1.2 - 1.0)

[0125] = 48.4 + 0.1 = 48.5

[0126] Training plan generation: The system recommends that Ms. Wang complete 50 knee flexion and extension trainings per day and gradually increase the training load.

[0127] Example 2: Detection of action deviation and real-time feedback during training;

[0128] When Ms. Wang completes the rehabilitation training at home, the system uses the knee joint monitoring device to detect the accuracy of the training movements in real time and provides corrective feedback.

[0129] Target movement setting:

[0130] Target movement angle: θ i deal = [30°, 60°, 90°].

[0131] Movement rhythm: Each set of movements is completed in 3 seconds.

[0132] Actual movement acquisition:

[0133] Actual movement angle: θ a ctual = [28°, 55°, 88°].

[0134] Calculation of movement deviation E:

[0135]

[0136] System feedback: It is detected that the movement deviation E = 9° > the threshold value of 5°.

[0137] The system corrects the movement through voice prompts and displays a standard movement video example.

[0138] Training intensity adjustment: The current intensity I = 96.8, adjustment formula:

[0139]

[0140] The system reduces the training intensity and recommends retraining after movement correction.

[0141] Example 3: Long-term rehabilitation evaluation and training optimization;

[0142] After 2 weeks of training, Ms. Wang needs to evaluate the rehabilitation effect and generate an optimized training plan for the next stage.

[0143] Data collection: Current range of motion R current = 2.3 rad; Current total load L current = 250 N·m / s 2 .

[0144] Rehabilitation index CI: Baseline data: R baseline = 2.5 rad, L b aseline = 300 N·m / s 2 .

[0145] Calculation of rehabilitation index:

[0146] Training intensity I: Weight factors k1 = 0.5, k2 = 0.5:

[0147] I = k1·R + k2·L = 0.5·2.3 + 0.5·250 = 126.15

[0148] Training load F: Target rehabilitation index CI target = 1.3, adjustment factor β = 0.6, γ = 0.4;

[0149] F = β·I + γ·(CI target - CI current ) = 0.6·126.15 + 0.4·(1.3 - 1.1)

[0150] = 75.69 + 0.08 = 75.77

[0151] Training optimization plan generation: The system recommends that Ms. Wang complete 76 knee flexion and extension trainings per day in the next stage, and increase the target range of the movement angle to [0°, 100°].

[0152] Finally, it should be noted that: The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: They can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A remote diagnosis and rehabilitation system for knee osteoarthritis, characterized in that: The system includes: Intelligent knee joint monitoring device: used to collect knee joint motion data, including knee joint motion angle θ(t), load pressure P(t) and motion acceleration a(t); Data analysis module: calculates the knee joint range of motion R, total joint load L, rehabilitation index CI and movement deviation E through formulas; Personalized rehabilitation program generation module: generates a dynamically adjusted personalized rehabilitation training program based on the rehabilitation index CI and training intensity I calculated by the data analysis module; Remote communication module: used for data transmission, diagnosis and treatment interaction, and training feedback between patients and doctors; Rehabilitation training guidance module: used to guide patients to complete training movements in real time and correct the patient's training process according to movement deviations.

2. The remote diagnosis and rehabilitation system for knee osteoarthritis according to claim 1, characterized in that: The motion data collected by the intelligent knee joint monitoring device include: knee joint activity angle θ(t), ranging from 0°≤θ(t)≤180°; Instantaneous load pressure P(t), unit is N; Instantaneous acceleration a(t), in m / s 2 , which satisfies the following derivation relationship: in, is the angular velocity, and x(t) is the knee joint displacement.

3. The remote diagnosis and rehabilitation system for knee osteoarthritis according to claim 1, characterized in that: The data analysis module calculates the knee joint range of motion R, the total joint load L and the rehabilitation index CI by the following formula, wherein the knee joint range of motion R is: Among them, R is in radians, and [t1, t2] is the acquisition time period; Total joint load L: Where, L is in N·m / s 2 , represents the total load borne by the joint; Recovery Index CI: Among them, CI is a dimensionless index, R baseline ,L baseline is the initial state of the patient, R current ,L current The current training status.

4. The remote diagnosis and rehabilitation system for knee osteoarthritis according to claim 3, characterized in that: The dynamic change trend of the rehabilitation index CI is predicted by the following formula: Rehabilitation index time change formula: Among them, T is the training cycle time, R baseline ,L baseline is the initial state of the patient, R current ,L current is the current training status; Predict the next round of recovery index CI t+1 : Among them, α is the adjustment factor, and the range is 0.1≤α≤0.

5.

5. The remote diagnosis and rehabilitation system for knee osteoarthritis according to claim 1, characterized in that: The personalized rehabilitation program generation module dynamically adjusts the patient's training load based on the rehabilitation index CI and the training intensity I: Training intensity calculation formula: I=k1·R+k2·L Among them, k1, k2 are weight factors, satisfying k1+k2=1; Training load adjustment formula: F=β I+γ (CI target -CI current ) Among them, β and γ are adjustment factors, ranging from β ≥ 0.1 and γ ≤ 1.

0.

6. The remote diagnosis and rehabilitation system for knee osteoarthritis according to claim 1, characterized in that: The rehabilitation training guidance module detects the deviation of the patient's movements through the following formula: Among them, E is in degrees, which represents the total amount of action deviation, n is the number of action sampling points, θ actual,i is the actual angle, θ ideal,i is the target angle.

7. The remote diagnosis and rehabilitation system for knee osteoarthritis according to claim 6, characterized in that: When the action deviation E>E threshold When , the system adjusts the training intensity by the following formula: Among them, E threshold is the action deviation threshold, the range is 5°≤E threshold ≤20°.

8. The remote diagnosis and rehabilitation system for knee osteoarthritis according to claim 1, characterized in that: The remote communication module supports data encryption using the following encryption formula: C=Enc(K,D) Among them, C is the encrypted data, K is the key, and D is the original data.

9. The remote diagnosis and rehabilitation system for knee osteoarthritis according to claim 1, characterized in that: The system calculates the overall rate of change of training effect using the following formula: Among them, ΔCI is the rate of change of rehabilitation effect, CI final Final recovery index (dimensionless), indicating the patient's recovery status at the end of the current stage of training, CI initial The initial recovery index (dimensionless) indicates the patient's recovery status at the beginning of the current stage of training.

10. The remote diagnosis and rehabilitation system for knee osteoarthritis according to claim 1, characterized in that: The system optimizes rehabilitation programs through the following formula: Among them, CI optimal is the optimized rehabilitation index, which is used to adjust the next round of training program. baseline ,L baseline is the initial state of the patient, R current ,L current The current training status.

Images