Meniscus postoperative magnetic hyperthermia nursing auxiliary system

Abstract

The invention relates to the technical field of nursing, and provides a magnetic hyperthermia nursing auxiliary system after a meniscus operation. The system comprises a multi-source information acquisition module, a motion behavior identification module, a magnetic hyperthermia parameter control module and a terminal monitoring display module. The multi-source information acquisition module is responsible for acquiring knee joint movement and regional temperature data of a patient and performing preprocessing and feature extraction on the data; the motion behavior recognition module evaluates the motion completion condition by analyzing the real-time motion trail and motion characteristics of the patient; the magnetic hyperthermia parameter control module adjusts output parameters of the magnetic hyperthermia equipment according to the identification result; and the terminal monitoring display module is used for displaying related data and providing an interaction function.

Description

Technical Field

[0001] The present invention relates to the field of nursing technology. More specifically, the present invention relates to a magnetic heat therapy nursing assistance system after meniscus surgery. Background Art

[0002] Magnetic heat therapy acts on magnetic materials through an alternating magnetic field to generate appropriate heat locally, thereby promoting blood circulation and tissue repair; while rehabilitation assistance technology focuses on accurately monitoring and analyzing the motion parameters of patients to optimize the postoperative recovery process. After minimally invasive surgery for meniscus injury, patients usually face problems such as soft tissue injury and limited knee joint function. How to combine heat therapy with motion analysis to provide efficient rehabilitation assistance has become an important research direction.

[0003] Literature 1 (Sharma A, et al., Design of a temperature-feedback controlled automated magnetic hyperthermia therapy device. Medical Physics, 2023) proposed a magnetic heat therapy device based on PID control. Its precise target temperature control and dynamic feedback regulation system significantly improve the efficiency and safety of heat therapy. Research shows that this device can not only quickly reach the set temperature but also maintain constant heat therapy conditions during the treatment process, avoiding tissue damage caused by overheating. These characteristics provide a theoretical basis for the application of magnetic heat therapy technology in postoperative rehabilitation and also provide a direction for the development of more integrated rehabilitation assistance systems.

[0004] In addition, Literature 2 (Espinosa A, et al., Janus magnetic-plasmonic nanoparticles for magnetically guided and thermally activated cancer therapy. Nature Nanotechnology, 2020) introduced a combined treatment strategy that combines magnetic heat therapy and photothermal therapy. Through the synergistic effect of magnetic and plasmonic nanoparticles, this technology achieves precise heat therapy localization and efficient energy conversion. It can concentrate nanoparticles in the target area through magnetic guidance and promote tissue repair through thermal activation. This technology based on multifunctional nanomaterials shows good application prospects and provides a reference for the further development of magnetic heat therapy technology.

[0005] However, although the magnetic hyperthermia combined with rehabilitation nursing technology shows potential in promoting tissue repair and improving the rehabilitation effect, its application in the postoperative rehabilitation of patients undergoing minimally invasive meniscus repair surgery still faces technical challenges. For example, existing systems have limited capabilities in analyzing the complex movement patterns of the knee joint and providing real-time feedback, making it difficult to dynamically adjust hyperthermia parameters to meet the personalized rehabilitation needs of patients. In addition, there is still a lack of a perfect solution for effectively linking motion behavior analysis with the output regulation of hyperthermia devices. These technical deficiencies limit the widespread application of magnetic hyperthermia technology in the postoperative rehabilitation scenario of meniscus repair. Summary of the Invention

[0006] To overcome the above-mentioned defects of the prior art, the present invention provides a magnetic hyperthermia nursing assistance system for postoperative meniscus repair. Aiming at the problem in the prior art of lacking the precise analysis of the complex movement patterns of the knee joint and the dynamic regulation linkage of hyperthermia devices, through the collaborative design of a multi-source information acquisition module, a motion behavior recognition module, and a magnetic hyperthermia parameter control module, the dynamic time warping algorithm and convolutional neural network are used to evaluate the action quality, and the magnetic field strength, frequency, and heating time are adjusted based on the fuzzy control algorithm to achieve real-time monitoring of the patient's motion state and intelligent adjustment of hyperthermia parameters, thereby assisting the rehabilitation nursing process.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A magnetic hyperthermia nursing assistance system for postoperative meniscus repair, including a multi-source information acquisition module and a terminal monitoring and display module, further including a motion behavior recognition module and a magnetic hyperthermia parameter control module; the motion behavior recognition module is used to identify the action execution state of the patient's knee joint during rehabilitation training based on the standard action template comparison algorithm and deep learning algorithm, calculate the trajectory similarity value between the patient's motion trajectory and the standard action template in real time using the dynamic time warping algorithm, and output the action matching degree through the convolutional neural network model, and evaluate the standard degree of the action by combining the current magnetic hyperthermia data to analyze the influence degree of hyperthermia parameters on the action completion quality.

[0009] The magnetic hyperthermia parameter control module is used to adjust the output parameters of the magnetic hyperthermia device in real time based on the fuzzy control algorithm. By receiving the action evaluation score output by the motion behavior recognition module and the temperature data collected by the thermal sensor, the adjustment amounts of the magnetic field strength, frequency, and heating time are generated using the fuzzy inference method and the centroid defuzzification process.

[0010] As a further solution of the present invention, this module receives the action evaluation score of the patient from the motion behavior recognition module, and at the same time collects the real-time temperature data of the knee joint area through the thermosensitive sensor array; then, preprocesses these input data and converts them into fuzzy variables, and fuzzifies them into semantic levels through a predefined membership function; subsequently, based on the fuzzy rule base constructed from expert experience, combines the fuzzy states of the action score and the temperature, and uses the fuzzy inference method to deduce the adjustment requirements for the magnetic field strength, frequency, and heating time, generating a corresponding fuzzy output set; then, adopts the centroid defuzzification method to convert the fuzzy output into specific adjustment amounts; finally, applies these adjustment amounts to the current parameters of the magnetothermal therapy device to complete real-time adjustment and ensure that the adjusted parameters are within the safe range. The entire process is executed in a loop by the microcontroller to achieve dynamic control of the hyperthermia device, thereby optimizing the rehabilitation effect of the patient.

[0011] As a further solution of the present invention, the multi-source information acquisition module is respectively connected to the motion behavior recognition module and the magnetothermal therapy parameter control module, the motion behavior recognition module is connected to the magnetothermal therapy parameter control module, the motion behavior recognition module is bidirectionally connected to the terminal monitoring and display module, and the magnetothermal therapy parameter control module is bidirectionally connected to the terminal monitoring and display module.

[0012] As a further solution of the present invention, the motion behavior recognition module includes the following steps:

[0013] Step A1, using a gyroscope to collect real-time joint angle data, mapping the data to the human anatomical standard coordinate system through coordinate system transformation, and using the dynamic time warping algorithm to match the real-time motion trajectory with the standard action template to calculate the trajectory similarity value.

[0014] Step A2, using an inertial measurement unit to collect the angular velocity and acceleration data during the knee joint movement, extracting time-domain and frequency-domain features to construct a motion feature matrix, inputting the feature matrix into a pre-trained convolutional neural network for processing, and outputting the action matching degree after feature extraction, dimensionality reduction, and full connection layer mapping.

[0015] Step A3, collecting the real-time temperature distribution data of the thermosensitive sensor array and the actual heating time of the magnetothermal therapy device, respectively calculating the deviation value between the current temperature and the target temperature, and the deviation value between the actual heating time and the preset time, and calculating the hyperthermia effect evaluation value based on these deviation values. Among them, the calculation formula of the hyperthermia effect evaluation value is:

[0016]

[0017] In the formula, γ and δ are weight coefficients, ΔT is the deviation between the current temperature and the target temperature, Δt is the deviation between the actual heating time and the preset time, Tmax is the maximum allowable temperature deviation, t max is the maximum allowable time deviation.

[0018] Since the hyperthermia effect mainly depends on the proximity of the current temperature and the actual heating time to the target temperature and the preset time, deviation terms ΔT and Δt are introduced to characterize the deviation of the actual hyperthermia parameters from the ideal state. Subsequently, to achieve the comparability of deviations with different dimensions, the deviations are normalized by the maximum allowable temperature deviation and the maximum allowable time deviation respectively, resulting in and Thereby, the deviation values are constrained within a unified range, facilitating subsequent comprehensive analysis. Furthermore, considering that the influence weights of temperature and time on the hyperthermia effect may vary, coefficients γ and δ are introduced to weight the normalized deviations respectively, forming terms. The weight coefficients can be adjusted according to experimental data or clinical experience to reflect the requirements of specific application scenarios.

[0019] As a further solution of the present invention, to make the evaluation value reach the maximum value of 1 under ideal conditions (i.e., ΔT = 0 and Δt = 0) and gradually decrease as the deviation increases, a formula is constructed in the form of 1-(…), so that the greater the deviation, the lower the evaluation value, thereby intuitively characterizing the quality of the hyperthermia effect.

[0020] Step A4, calculate the action evaluation score based on the trajectory similarity value, action matching degree, and hyperthermia effect evaluation value calculated in the foregoing steps. Perform time series analysis on the sequence of action evaluation scores in multiple consecutive training cycles, and use linear correlation analysis to calculate the correlation coefficient between the action evaluation score and the hyperthermia effect evaluation value. Among them, the calculation formula of the action evaluation score is:

[0021]

[0022] In the formula, θ is the real-time joint angle sequence, θ s is the standard action template angle sequence, DTW(θ,θ s ) is the trajectory similarity value, M is the real-time motion feature matrix, M s is the standard action feature matrix, CNN(M,M s ) is the action matching degree, T is the current hyperthermia parameter matrix, T s is the target hyperthermia parameter matrix, H(T,T s ) is the hyperthermia effect evaluation function.

[0023] Dynamic Time Warping (DTW) is a method widely used in time series analysis. It can measure the similarity between two sequences, even if they are stretched or compressed on the time axis. DTW calculates the optimal matching path between two sequences through dynamic programming and outputs the cumulative distance. In rehabilitation training, the speed and amplitude of the patient's movements may vary due to individual differences. DTW can ignore these non-essential differences and focus on the overall consistency of the movement trajectories. After calculating the minimum distance between the real-time joint angle sequence and the standard movement template angle sequence, DTW normalizes it into a similarity score.

[0024] Convolutional Neural Network (CNN) performs excellently in feature extraction and pattern recognition. It can learn local features from complex data and perform classification or regression. In the present invention, the movement data of the patient is collected by sensors to generate a feature matrix. The CNN model learns the feature matrix of the standard movement through training and outputs the matching degree score between the real-time movement and the standard movement.

[0025] Hyperthermia can affect the patient's muscle state and movement execution ability. H(T,T s ) evaluates the proximity of the current hyperthermia parameters to the target parameters. A value close to 1 indicates ideal hyperthermia, and a deviation from 1 indicates poor hyperthermia effect.

[0026] As a further solution of the present invention, a multi-objective evaluation method is adopted. The trajectory similarity value and the movement matching degree are multiplied to comprehensively consider the overall consistency and local details of the movement, reflecting their synergistic effect. The denominator is used as a regulating term. When the hyperthermia is ideal, the denominator is 1, and the score is determined by the trajectory similarity value and the movement matching degree. When the hyperthermia effect is poor, the denominator is greater than 1, and the score decreases. The square root form can smooth the adjustment effect and avoid drastic changes in the score due to excessive hyperthermia deviation.

[0027] As a further solution of the present invention, the specific implementation steps of the magnetic hyperthermia parameter control module include:

[0028] Step B1: Receive the action evaluation score output by the movement behavior recognition module and the temperature data collected by the current thermosensor, and calculate the action deviation value and the temperature deviation value;

[0029] Step B2: Establish a fuzzy rule base in the form of "if-then" based on expert experience. Determine the adjustment strategies for the magnetic field intensity, frequency, and heating time for different input combinations. Adjust the priority of the fuzzy rules in combination with the correlation value between the action evaluation score and the hyperthermia effect evaluation value, and perform fuzzy reasoning using the traditional fuzzy reasoning method;

[0030] Step B3: Perform defuzzification processing on the fuzzy reasoning result using the centroid method to obtain the adjustment amounts of the magnetic field intensity, frequency, and heating time;

[0031] Step B4: Superimpose the calculated adjustment amount on the current parameter value to obtain an updated control parameter, and ensure that it does not exceed the set safety range.

[0032] As a further solution of the present invention, the multi-source information acquisition module includes an inertial measurement unit, a thermal sensor unit, a data preprocessing unit, and a feature extraction unit; the inertial measurement unit uses a three-axis accelerometer and a three-axis gyroscope to collect the angle, angular velocity, and acceleration data of the patient's knee joint in real time; the thermal sensor unit uses an array of flexible thermistors to record the skin surface temperature changes in the knee joint area in real time; the data preprocessing unit performs noise reduction processing on the motion data and temperature data through wavelet transform, and realizes the time synchronization of multi-modal data based on the timestamp matching method; the feature extraction unit extracts time-domain and frequency-domain features from the motion data, including the angle change rate, the peak value of angular acceleration, and the motion smoothness, and extracts the temperature mean square deviation and temperature change rate features from the hyperthermia data.

[0033] As a further solution of the present invention, the terminal monitoring and display module includes a data display unit and a data transmission unit; the data display unit is used to display the patient's action execution status, action evaluation score, trajectory similarity value, action matching degree, hyperthermia effect evaluation value, and the operating parameters of the magnetothermal therapy device on the terminal interface in real time; the data transmission unit is used to transmit the patient's real-time joint angle sequence, motion feature matrix, thermal sensor temperature distribution data, and the adjustment amounts of magnetic field strength, frequency, and heating time to the remote monitoring platform through wireless communication for storage and analysis.

[0034] An electronic device includes: a processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the above-mentioned magnetothermal therapy nursing assistance system for post-meniscus surgery by calling the computer program stored in the memory.

[0035] A computer-readable storage medium stores instructions that, when run on a computer, cause the computer to execute the above-mentioned magnetothermal therapy nursing assistance system for post-meniscus surgery.

[0036] Compared with the prior art, the beneficial effects of the magnetothermal therapy nursing assistance system for post-meniscus surgery of the present invention are as follows:

[0037] The present invention can identify the action execution status of the patient's knee joint in real time by designing a motion behavior recognition module based on the standard action template comparison algorithm and the deep learning algorithm. The dynamic time warping algorithm is used to calculate the trajectory similarity value between the motion trajectory and the standard action template, and the action matching degree is output by combining the convolutional neural network model. At the same time, the influence degree of the thermotherapy parameters on the action completion quality is combined to form a comprehensive action evaluation score. In contrast, the magnetothermal therapy devices in the prior art usually only focus on the precise regulation of the thermotherapy parameters, lack the monitoring function that is real-time associated with the patient's motion behavior, and cannot evaluate the influence of the action quality on the rehabilitation process, resulting in the failure to form an effective collaborative optimization between thermotherapy and rehabilitation training.

[0038] The present invention realizes the dynamic adjustment of the output parameters of the magnetothermal therapy device through the magnetothermal therapy parameter control module based on the fuzzy control algorithm. The module can receive the action evaluation score and the temperature data collected by the thermal sensor, and adjust the magnetic field intensity, frequency and heating time in real time through the fuzzy inference and the centroid defuzzification method to ensure that the thermotherapy conditions can adapt to the rehabilitation needs of the patient. Brief Description of the Drawings

[0039] Figure 1 It is a diagram of a knee joint rehabilitation nursing device.

[0040] Figure 2 It is a diagram of the design and temperature distribution analysis of the magnetothermal therapy system based on PID control in Document 1.

[0041] Figure 3 It is a schematic structural diagram of a magnetothermal therapy nursing assistance system for a patient after meniscus surgery according to the present invention.

[0042] Figure 4 It is a temperature distribution diagram of the thermal sensor of a magnetothermal therapy nursing assistance system for a patient after meniscus surgery according to the present invention.

[0043] Figure 5 It is a schematic diagram of the terminal interface of a magnetothermal therapy nursing assistance system for a patient after meniscus surgery according to the present invention.

[0044] In the figure, PID Controller: Proportional-Integral-Derivative Controller; e(t): Error signal; u_ctrl: Control signal; T_ref: Reference temperature; T_probe: Probe temperature; Feedback Signal: Feedback signal; Sensor noise: Sensor noise; RF Coil: Radio frequency coil; Matching Network: Matching network; 4x Fiber Optic Temperature Probe Chassis: Four groups of fiber optic temperature probe chassis; Im(s): Imaginary part of the s-plane; Re(s): Real part of the s-plane; sin^(-1)ζ: Arcsine of the damping ratio; ω_n: Natural frequency; σ: Convergence rate; Agarose gel: Agarose gel; Cu wire: Copper wire; Temperature: Temperature; AMF treatment: Alternating magnetic field treatment. Detailed implementation manner

[0045] The following will clearly and completely describe the technical solutions in this embodiment with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0046] Embodiment 1

[0047] A magnetic thermotherapy nursing assistance system after meniscus surgery includes a multi-source information acquisition module, a motion behavior recognition module, a magnetic thermotherapy parameter control module, and a terminal monitoring and display module.

[0048] In the embodiments of the present invention, the multi-source information acquisition module is respectively connected to the motion behavior recognition module and the magnetic thermotherapy parameter control module, the motion behavior recognition module is connected to the magnetic thermotherapy parameter control module, the motion behavior recognition module is bidirectionally connected to the terminal monitoring and display module, and the magnetic thermotherapy parameter control module is bidirectionally connected to the terminal monitoring and display module.

[0049] The multi-source information acquisition module includes an inertial measurement unit, a thermosensitive sensor unit, a data preprocessing unit, and a feature extraction unit; the inertial measurement unit uses a three-axis accelerometer and a three-axis gyroscope to collect the angle, angular velocity, and acceleration data of the patient's knee joint in real time, with a sampling frequency of 100 Hz; the thermosensitive sensor unit uses 16 flexible thermistors arranged in a 4×4 array to record the skin surface temperature changes in the knee joint area in real time, with a sampling frequency of 1 Hz; the data preprocessing unit performs 4-layer decomposition and noise reduction processing on the motion data and temperature data through db4 wavelet transform, and realizes the time synchronization of multi-modal data based on the timestamp matching method; the feature extraction unit extracts time-domain and frequency-domain features from the motion data, including the angle change rate, the peak value of angular acceleration, and the motion smoothness, and extracts the temperature mean square deviation and temperature change rate features from the hyperthermia data, providing a data basis for action recognition and analysis.

[0050] The motion behavior recognition module is used to recognize the action execution state of the patient based on the standard action template comparison algorithm and the deep learning algorithm. It uses the dynamic time warping algorithm to calculate the trajectory similarity value between the knee joint motion trajectory of the patient during the rehabilitation training process and the standard action template in real time, and outputs the action matching degree through the convolutional neural network model, and combines the current magnetothermal therapy data to analyze the influence degree of the hyperthermia parameters on the action completion quality.

[0051] The motion behavior recognition module in the embodiment of the present invention includes the following steps:

[0052] Step A1: Use the gyroscope to collect real-time joint angle data, map the data to the human anatomy standard coordinate system through coordinate transformation, and use the dynamic time warping algorithm to match the real-time motion trajectory with the standard action template to calculate the trajectory similarity value;

[0053] Step A2: Use the inertial measurement unit to collect the angular velocity and acceleration data during the knee joint motion, extract time-domain and frequency-domain features to construct a motion feature matrix, input the feature matrix into a pre-trained convolutional neural network for processing, and output the action matching degree after feature extraction, dimensionality reduction, and full connection layer mapping;

[0054] Step A3: Collect the real-time temperature distribution data of the thermosensitive sensor array and the actual heating time of the magnetothermal therapy device, calculate the deviation value between the current temperature and the target temperature and the deviation value between the actual heating time and the preset time respectively, and calculate the hyperthermia effect evaluation value based on these deviation values. Among them, the calculation formula of the hyperthermia effect evaluation value is:

[0055]

[0056] In the formula, γ and δ are weight coefficients, ΔT is the deviation between the current temperature and the target temperature, Δt is the deviation between the actual heating time and the preset time, Tmax is the maximum allowable temperature deviation, t max is the maximum allowable time deviation;

[0057] Step A4, calculate the action evaluation score based on the trajectory similarity value, action matching degree, and hyperthermia effect evaluation value calculated in the foregoing steps. Perform time series analysis on the action evaluation score sequence in multiple consecutive training cycles, and use linear correlation analysis to calculate the correlation coefficient between the action evaluation score and the hyperthermia effect evaluation value. Among them, the calculation formula for the action evaluation score is:

[0058]

[0059] In the formula, θ is the real-time joint angle sequence, θ s is the standard action template angle sequence, DTW(θ, θ s ) is the similarity value obtained by calculating the joint angle sequence θ and the standard action template sequence θ s through the dynamic time warping algorithm, M is the real-time motion feature matrix, M s is the standard action feature matrix, CNN(M, M s ) is the action matching degree output after inputting the real-time motion feature matrix M and the standard feature matrix M s into the convolutional neural network, T is the current hyperthermia parameter matrix, T s is the target hyperthermia parameter matrix, H(T, T s ) is the hyperthermia effect evaluation function.

[0060] In the embodiment of the present invention, in view of the fact that the hyperthermia effect mainly depends on the proximity of the current temperature and the actual heating time to the target temperature and the preset time, deviation terms ΔT and Δt are introduced to characterize the deviation of the actual hyperthermia parameters from the ideal state. Subsequently, to achieve the comparability of deviations with different dimensions, the deviations are normalized respectively with the maximum allowable temperature deviation and the maximum time deviation, and and are obtained, so as to constrain the deviation values within a unified range, facilitating subsequent comprehensive analysis. Furthermore, considering that the influence weights of temperature and time on the hyperthermia effect may be different, coefficients γ and δ are introduced to weight the normalized deviations respectively, forming terms. The weight coefficients can be adjusted according to experimental data or clinical experience to reflect the requirements of specific application scenarios.

[0061] In the embodiment of the present invention, to make the evaluation value reach the maximum value of 1 under ideal conditions (i.e., ΔT = 0 and Δt = 0) and gradually decrease as the deviation increases, the formula is constructed in the form of 1-(...), so that the greater the deviation, the lower the evaluation value, thus intuitively characterizing the quality of the hyperthermia effect.

[0062] The magnetic hyperthermia parameter control module is used to adjust the output parameters of the magnetic hyperthermia device in real time based on the fuzzy control algorithm. By receiving the action evaluation score output by the motion behavior recognition module and the temperature data collected by the thermal sensor, the Mamdani inference method is used in combination with the centroid defuzzification process to generate the adjustment amounts of the magnetic field intensity, frequency, and heating time.

[0063] The specific implementation steps of the magnetic hyperthermia parameter control module in the embodiments of the present invention include:

[0064] Step B1: Receive the action evaluation score output by the motion behavior recognition module and the temperature data collected by the current thermal sensor, and calculate the action deviation value and the temperature deviation value. The calculation formula for the action deviation value is:

[0065] E = 1 - S;

[0066] In the formula, E is the action deviation value, and S is the action evaluation score;

[0067] Step B2: Establish a fuzzy rule base in the form of "if-then" based on expert experience. Determine the adjustment strategies for the magnetic field intensity, frequency, and heating time for different input combinations, and dynamically adjust the priority of the fuzzy rules in combination with the Pearson correlation coefficient value. Among them, the rules with high correlation are preferentially applied to fuzzy reasoning, and the rules with low correlation are degraded to auxiliary rules to improve the accuracy and adaptability of reasoning;

[0068] Step B3: Perform fuzzy reasoning using the Mamdani inference method, and perform defuzzification on the fuzzy reasoning result using the centroid method to obtain the adjustment amounts of the magnetic field intensity, frequency, and heating time. The calculation formula is:

[0069]

[0070] In the formula, ΔX is the adjustment amount of the parameter, that is, the value size that needs to be adjusted, x is the variable in the output universe of discourse, and μ(x) is the membership degree corresponding to each possible output value x in the fuzzy set obtained after fuzzy reasoning;

[0071] Step B4: Superimpose the calculated adjustment amount on the current parameter value to obtain the updated control parameter, and ensure that it does not exceed the set safety range.

[0072] The rule examples in the embodiments of the present invention are as follows:

[0073] When the absolute value of the Pearson correlation coefficient is relatively large and the rule weight is relatively high:

[0074] Rule 1, IF the action evaluation deviation is negative large AND the temperature deviation is too low THEN increase the magnetic field intensity AND increase the frequency AND extend the heating time;

[0075] Rule 2, IF the action evaluation deviation is a small positive value AND the temperature deviation is on the high side, THEN the magnetic field strength is decreased AND the frequency is decreased AND the heating time is shortened;

[0076] When the absolute value of the Pearson correlation coefficient is small and the rule weight is low, it is only applied as an auxiliary rule:

[0077] Rule 3, IF the action evaluation deviation is a medium negative value AND the temperature deviation is moderate, THEN the magnetic field strength is slightly increased AND the frequency remains unchanged AND the heating time is slightly extended;

[0078] Rule 4, IF the action evaluation deviation is a large positive value AND the temperature deviation is on the high side, THEN the magnetic field strength is decreased by a large margin AND the frequency is decreased AND the heating time is greatly shortened.

[0079] The terminal monitoring and display module includes a data display unit and a data transmission unit; the data display unit is used to display the patient's action execution status, action evaluation score, trajectory similarity value, action matching degree, hyperthermia effect evaluation value, and the operating parameters of the magnetic hyperthermia device in real time on the terminal interface; the data transmission unit is used to transmit the patient's real-time joint angle sequence, motion feature matrix, temperature distribution data of the thermal sensor, and the adjustment amounts of the magnetic field strength, frequency, and heating time to the remote monitoring platform through wireless communication for storage and analysis.

[0080] An electronic device includes: a processor and a memory, wherein, a computer program that can be called by the processor is stored in the memory; the processor executes a magnetic hyperthermia nursing assistance system after meniscus surgery as described above by calling the computer program stored in the memory.

[0081] A computer-readable storage medium stores instructions, and when the instructions run on a computer, the computer executes a magnetic hyperthermia nursing assistance system after meniscus surgery as described above.

[0082] Embodiment 2

[0083] The motion behavior recognition module is used to recognize the patient's action execution status based on the standard action template comparison algorithm and the deep learning algorithm, calculate the trajectory similarity value between the knee joint movement trajectory of the patient during the rehabilitation training and the standard action template in real time by using the dynamic time warping algorithm, and output the action matching degree through the convolutional neural network model, and combine the current magnetic hyperthermia data to analyze the influence degree of the hyperthermia parameters on the action completion quality.

[0084] The motion behavior recognition module in the embodiment of the present invention includes the following steps:

[0085] Step A1: Use the MPU6050 six-axis inertial measurement unit to collect knee joint motion data with a sampling frequency of 100 Hz. Perform attitude calculation using the quaternion method to convert the collected data from the sensor coordinate system to the human anatomical standard coordinate system, obtaining the angle sequence in the standard coordinate system. Subsequently, use the dynamic time warping (DTW) algorithm to calculate the similarity between the real-time trajectory and the standard template. The quaternion update formula is as follows:

[0086] q(t + 1) = q(t) + 0.5 × q(t) × Ω(ω x , ω y , ω z ) × Δt 1 ;

[0087] In the formula, q is the quaternion, Ω is the angular velocity matrix, and ω x , ω y , ω z are the three-axis angular velocity values, and Δt 1 is the sampling period;

[0088] The distance calculation of DTW uses the dynamic programming recurrence formula:

[0089] D(i, j) = d(p i , q j ) + min{D(i - 1, j), D(i - 1, j - 1), D(i, j - 1)}

[0090] In the formula, d(p i , q j ) is the Euclidean distance between two sampling points;

[0091] Step A2: The original data obtained from the inertial measurement unit includes three-axis angular velocity and three-axis acceleration. Extract features from these data to construct a motion feature matrix, including time-domain features and frequency-domain features. Among them, the time-domain features include mean, standard deviation, kurtosis, and skewness; the frequency-domain features include: calculating the power spectral density through the fast Fourier transform and extracting features using the kurtosis calculation formula; the constructed convolutional neural network contains two convolutional layers, two max-pooling layers, and one fully connected layer. The activation function uses ReLU to output the action matching degree;

[0092] Step A3: Collect the real-time temperature distribution data of the thermosensor array and the actual heating time of the magnetothermal therapy device, calculate the deviation value between the current temperature and the target temperature and the deviation value between the actual heating time and the preset time respectively, and calculate the thermotherapy effect evaluation value based on these deviation values. The calculation formula of the thermotherapy effect evaluation value is as follows:

[0093]

[0094] where γ and δ are weight coefficients, ΔT is the deviation between the current temperature and the target temperature, Δt is the deviation between the actual heating time and the preset time, T max is the maximum allowable temperature deviation, t max is the maximum allowable time deviation;

[0095] Step A4, calculate the action evaluation score, and then perform time series analysis on the score sequence of 20 consecutive training cycles, and use the Pearson correlation coefficient to evaluate the correlation between the hyperthermia effect and the action improvement:

[0096] Among them, the calculation formula of the action evaluation score is:

[0097]

[0098] where θ is the real-time joint angle sequence, θ s is the standard action template angle sequence, DTW(θ,θ s ) is the similarity value calculated by the dynamic time warping algorithm for the joint angle sequence θ and the standard action template sequence θ s , M is the real-time motion feature matrix, M s is the standard action feature matrix, CNN(M,M s ) is the action matching degree output after inputting the real-time motion feature matrix M and the standard feature matrix M s into the convolutional neural network, T is the current hyperthermia parameter matrix, T s is the target hyperthermia parameter matrix, H(T,T s ) is the hyperthermia effect evaluation function;

[0099] The calculation formula of the Pearson correlation coefficient is:

[0100]

[0101] where x k is the action evaluation score in the k-th training cycle, y k is the hyperthermia effect evaluation value in the corresponding cycle, and are the average values of x k and y k respectively.

[0102] The following is a Python code example, including obtaining motion behavior recognition and hyperthermia effect evaluation by the motion behavior recognition module. Note that this example is only a starting point and may need to be adjusted according to the actual situation and device interface in actual applications.

[0103]

[0104]

[0105]

[0106]

[0107]

[0108]

[0109]

[0110]

[0111] This code is only for example, and appropriate modifications and adjustments need to be made according to specific situations in actual applications.

[0112] This embodiment verifies the effectiveness of the system in evaluating the quality of patients' rehabilitation training through specific experimental data. The system can accurately capture the movement characteristics of patients and provide quantitative evaluation results, providing an important reference basis for clinical rehabilitation training.

[0113] Example 3

[0114] This embodiment of the present invention is directed to a 35-year-old male patient on the 21st day after partial meniscectomy (minimally invasive), weighing 70 kg, with the rehabilitation goal of restoring knee flexion and extension function. The system configuration includes:

[0115] Inertial measurement unit (IMU): An MPU6050 six-axis sensor is used, including a three-axis accelerometer and a three-axis gyroscope, with a sampling frequency of 100 Hz, fixed on the outside of the patient's knee joint.

[0116] Thermal sensor unit: 16 flexible thermistors in a 4×4 array are used, covering the knee joint area, with a sampling frequency of 1 Hz and a temperature measurement range of 30°C to 45°C.

[0117] The initial parameters of the magnetic heat therapy device are shown in Table 1:

[0118] Table 1

[0119] Magnetic field strength Frequency Heating time 100 A / m 50 kHz 300 s (5 minutes)

[0120] The target parameters are shown in Table 2:

[0121] Table 2

[0122] Target temperature Preset heating time Allowable maximum temperature deviation Allowable maximum time deviation 38℃ 300s 2℃ 60

[0123] In an embodiment of the present invention, the patient performs a knee flexion and extension movement once, lasting for 5 seconds. The IMU collects motion data of 500 sampling points, including knee joint angle, angular velocity, and acceleration. The thermosensitive sensor synchronously records the temperature distribution in the knee joint area.

[0124] In an embodiment of the present invention, the IMU measures the knee joint angle sequence, which increases from the starting angle of 10° to the maximum flexion angle of 90°, and then returns to the ending angle of 15°. The standard action template is a starting angle of 0°, a maximum flexion angle of 100°, and an ending angle of 0°.

[0125] In an embodiment of the present invention, the average temperature of 16 points measured by the thermosensitive sensor array is 37.2°C.

[0126] The motion behavior recognition module performs the following steps according to the collected data:

[0127] Step A1, use the dynamic time warping algorithm to compare the real-time angle sequence with the standard template. DTW calculates the optimal matching path of the two sequences through dynamic programming, and the cumulative distance is 150 (unit: degree). After normalization, the trajectory similarity is 0.85. This value indicates that the patient's action trajectory is highly similar to the standard template, with only a slight difference due to a slightly smaller amplitude.

[0128] Step A2, extract time-domain features (mean, standard deviation) and frequency-domain features (power spectral density) from the angular velocity and acceleration data to generate a motion feature matrix. The standard feature matrix comes from a pre-trained data set. Input a convolutional neural network with two convolutional layers and one fully connected layer, the activation function is ReLU, and the output action matching degree is 0.80. This result reflects that the action details are executed well, but it does not fully meet the standard.

[0129] Step A3, collect the real-time temperature distribution data of the thermosensitive sensor array and the actual heating time of the magnetothermal therapy device, calculate the deviation value between the current temperature and the target temperature and the deviation value between the actual heating time and the preset time respectively, and calculate the hyperthermia effect evaluation value based on these deviation values. Among them, the calculation formula of the hyperthermia effect evaluation value is:

[0130]

[0131] The hyperthermia effect evaluation value is 0.76, indicating that the hyperthermia conditions are good, but it does not reach the best due to a slightly lower temperature.

[0132] Step A4, calculate the action evaluation score:

[0133]

[0134] The action evaluation score is 0.61, indicating that the action quality is above medium, affected by the slightly lower hyperthermia effect.

[0135] The magnetothermal therapy parameter control module receives the action evaluation score and the temperature, and executes the following steps:

[0136] Step B1: Receive the action evaluation score output by the motion behavior recognition module and the temperature data collected by the current thermal sensor, and calculate the action deviation value and the temperature deviation value. Among them, the action deviation value is 0.39, indicating that the action quality is lower than the ideal level; the temperature deviation value is -0.8 °C, indicating that the current temperature is slightly lower than the target value.

[0137] Step B2: Establish a fuzzy rule base in the form of "if-then" based on expert experience, determine the adjustment strategies for the magnetic field strength, frequency, and heating time for different input combinations, adjust the priority of the fuzzy rules in combination with the correlation coefficient between the action evaluation score and the hyperthermia effect evaluation value, and perform fuzzy reasoning using the traditional fuzzy reasoning method.

[0138] In the embodiment of the present invention, the system has pre-established a fuzzy rule base based on expert experience, using the action deviation and the temperature deviation as inputs, and the adjustment amounts of the magnetic field strength, frequency, and heating time as outputs. The fuzzy variables are defined as follows:

[0139] Action deviation: divided into "negative large (ND)", "negative small (NS)", "zero (ZE)", "positive small (PS)", "positive large (PD)".

[0140] Temperature deviation: divided into "too low (TL)", "slightly low (SL)", "moderate (OK)", "slightly high (SH)", "too high (TH)".

[0141] After input fuzzyfication, the action deviation is 0.39, belonging to "positive small (PS)" (membership degree 0.7) and "positive large (PD)" (membership degree 0.3); the temperature deviation is -0.8 °C, belonging to "slightly low (SL)" (membership degree 0.8) and "moderate (OK)" (membership degree 0.2). Example rules include:

[0142] Rule 1: IF the action deviation is PS AND the temperature deviation is SL THEN the magnetic field strength "increases (PI)", the frequency "increases (PI)", and the heating time "lengthens (PL)".

[0143] Rule 2: IF the action deviation is PD AND the temperature deviation is SL THEN the magnetic field strength "increases significantly (PD)", the frequency "increases (PI)", and the heating time "lengthens (PL)".

[0144] Combined with the Pearson correlation coefficient of the action evaluation score and the hyperthermia effect evaluation value, the rules with higher correlation have higher priorities. Using the Mamdani fuzzy reasoning method, calculate the rule activation degree and generate a fuzzy output set.

[0145] Step B3: The center of gravity method is used to defuzzify the fuzzy inference results to obtain the magnetic field strength adjustment amount, frequency adjustment amount, and heating time adjustment amount.

[0146] The center of gravity method is applied to defuzzify the output set generated by fuzzy inference. The output fuzzy set includes "decrease (NS)", "unchanged (ZE)", "increase (PI)", etc. Taking the magnetic field strength as an example, Rule 1 outputs "increase (PI)" (center value 10 A / m, membership degree 0.7), and Rule 2 outputs "large increase (PD)" (center value 20 A / m, membership degree 0.3). The calculation by the center of gravity method is as follows:

[0147]

[0148] Similarly, the frequency adjustment amount Δf = 5 kHz, and the heating time adjustment amount Δt = 30 s. For simplicity of control, they are adjusted to integer values, and finally, ΔB = 10 A / m, Δf = 5 kHz, and Δt = 30 s are taken.

[0149] Step B4: The calculated adjustment amounts are superimposed on the current parameter values to obtain the updated control parameters, and it is ensured that they do not exceed the set safety range. The updated control parameters are shown in Table 3:

[0150] Magnetic field strength Frequency Heating time 110 A / m 55 kHz 330s

[0151] As Figure 5 shown is the terminal interface in the embodiment of the present invention.

[0152] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claimed rights.

[0153] Finally: The above is only the preferred embodiment of the present invention and is not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A post-operative magnetic hyperthermia nursing assistance system for meniscus, comprising a multi-source information acquisition module and a terminal monitoring and display module, characterized in that , also includes a motion behavior recognition module and a magnetic hyperthermia parameter control module; the motion behavior recognition module is used to identify the patient's knee joint action execution state during rehabilitation training based on the standard action template comparison algorithm and the deep learning algorithm, and use the dynamic time warping algorithm to calculate the trajectory similarity value between the patient's motion trajectory and the standard action template in real time, and output the action matching degree through the convolutional neural network model, and analyze the influence of the hyperthermia parameters on the action completion quality in combination with the current magnetic hyperthermia data, and evaluate the standard degree of the action; The magnetic hyperthermia parameter control module is used to adjust the output parameters of the magnetic hyperthermia device in real time based on the fuzzy control algorithm. By receiving the action evaluation score output by the motion behavior recognition module and the temperature data collected by the thermistor, the fuzzy reasoning method is used in conjunction with the center of gravity defuzzification processing to generate the adjustment amount of the magnetic field intensity, frequency and heating time.

2. The magnetic hyperthermia nursing assistance system for meniscus surgery according to claim 1, characterized in that: The multi-source information acquisition module is respectively connected to the motion behavior recognition module and the magnetic hyperthermia parameter control module, the motion behavior recognition module is connected to the magnetic hyperthermia parameter control module, the motion behavior recognition module is bidirectionally connected to the terminal monitoring and display module, and the magnetic hyperthermia parameter control module is bidirectionally connected to the terminal monitoring and display module.

3. The magnetic hyperthermia nursing assistance system for meniscus surgery according to claim 1, characterized in that: The sports behavior recognition module comprises the following steps: Step A1, using a gyroscope to collect real-time joint angle data, mapping the data to the standard human anatomical coordinate system through coordinate system transformation, using a dynamic time warping algorithm to match the real-time motion trajectory with the standard motion template, and calculating the trajectory similarity value; Step A2, using an inertial measurement unit to collect angular velocity and acceleration data during knee joint movement, extracting time domain and frequency domain features to construct a motion feature matrix, inputting the feature matrix into a pre-trained convolutional neural network for processing, and outputting the motion matching degree after feature extraction, dimensionality reduction, and full connection layer mapping; Step A3, collecting the real-time temperature distribution data of the thermosensitive sensor array and the actual heating time of the magnetic hyperthermia device, respectively calculating the deviation between the current temperature and the target temperature, and the deviation between the actual heating time and the preset time, and calculating the hyperthermia effect evaluation value based on these deviation values, wherein the calculation formula of the hyperthermia effect evaluation value is: In the formula, γ and δ are weight coefficients, ΔT is the deviation between the current temperature and the target temperature, Δt is the deviation between the actual heating time and the preset time, and T max is the maximum allowable temperature deviation, t max is the maximum allowed time deviation; Step A4, based on the trajectory similarity value, action matching degree and thermal therapy effect evaluation value calculated in the above steps, the action evaluation score is calculated, and the action evaluation score sequence in multiple consecutive training cycles is analyzed in time series, and the correlation coefficient between the action evaluation score and the thermal therapy effect evaluation value is calculated by linear correlation analysis, wherein the calculation formula of the action evaluation score is: Where, θ is the real-time joint angle sequence, θ s is the standard action template angle sequence, DTW(θ,θ s ) is the trajectory similarity value, M is the real-time motion feature matrix, M s is the standard action feature matrix, CNN(M,M s ) is the action matching degree, T is the current thermal therapy parameter matrix, T s is the target hyperthermia parameter matrix, H(T,T s ) is the evaluation function of the thermal therapy effect.

4. The magnetic hyperthermia nursing assistance system for meniscus surgery according to claim 1, characterized in that: The specific implementation steps of the magnetic hyperthermia parameter control module include: Step B1, receiving the action evaluation score output by the motion behavior recognition module and the temperature data collected by the current thermistor, and calculating the action deviation value and the temperature deviation value; Step B2, based on expert experience, a fuzzy rule base in the form of "if-then" is established to determine the adjustment strategy of magnetic field intensity, frequency and heating time for different input combinations, and the priority of fuzzy rules is adjusted in combination with the correlation value between the action evaluation score and the thermal therapy effect evaluation value, and fuzzy reasoning is performed using traditional fuzzy reasoning methods; Step B3, using the centroid method to defuzzify the fuzzy reasoning result to obtain the magnetic field intensity adjustment amount, the frequency adjustment amount and the heating time adjustment amount; Step B4, superimposing the calculated adjustment amount on the current parameter value to obtain an updated control parameter, and ensuring that it does not exceed a set safety range.

5. The magnetic hyperthermia nursing assistance system for meniscus surgery according to claim 1, characterized in that: The multi-source information acquisition module includes an inertial measurement unit, a thermal sensor unit, a data preprocessing unit and a feature extraction unit; the inertial measurement unit uses a three-axis accelerometer and a three-axis gyroscope to collect the angle, angular velocity and acceleration data of the patient's knee joint in real time; the thermal sensor unit uses an array of flexible thermistors to record the skin surface temperature changes in the knee joint area in real time; the data preprocessing unit performs noise reduction processing on the motion data and temperature data through wavelet transform, and realizes the time synchronization of multimodal data based on the timestamp matching method; The feature extraction unit extracts time domain and frequency domain features from the motion data, including angle change rate, angular acceleration peak value and motion smoothness, and extracts temperature mean square error and temperature change rate features from the hyperthermia data.

6. The magnetic hyperthermia nursing assistance system for meniscus surgery according to claim 1, characterized in that: The terminal monitoring and display module includes a data display unit and a data transmission unit; the data display unit is used to display the patient's action execution status, action evaluation score, trajectory similarity value, action matching degree, thermal therapy effect evaluation value and operating parameters of the magnetic thermal therapy equipment in real time on the terminal interface; the data transmission unit is used to transmit the patient's real-time joint angle sequence, motion feature matrix, thermistor temperature distribution data and magnetic field strength, frequency and heating time adjustment amount to the remote monitoring platform for storage and analysis via wireless communication.

7. An electronic device comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; characterized in that the processor executes a magnetic hyperthermia care auxiliary system for meniscus surgery as described in any one of claims 1-6 by calling the computer program stored in the memory.

8. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are run on a computer, the computer is caused to execute a magnetic hyperthermia nursing auxiliary system for meniscus surgery as described in any one of claims 1-6.

Images