Control method and system for child orthopedic traction auxiliary tool
Through the control system of the pediatric orthopedic traction assistance tool, combined with the pre-trained model and input of medical staff, the traction strategy is automatically determined and optimized, and the problem of low reliability and accuracy of traction strategies in the existing technology is solved, and the traction of pediatric orthopedic traction is realized Safe and effective treatment.
Patent Information
- Application Number
- CN202411385825.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-30
- Publication Date
- 2024-11-15
AI Technical Summary
The reliability and accuracy of pediatric orthopedic traction strategies in the prior art lead to poor treatment effects and may even damage the patient's body.
A control system for children's orthopedic traction auxiliary tools is designed, including electric traction components, human-computer interaction modules and main processors. By receiving disease description information and patient characteristic information, combined with pre-trained traction parameters, we determine the model and input from medical staff. The strategy is to automatically determine the final traction strategy, and collect the electromyography and pressure signals through wearable devices for real-time adjustments, and optimize the traction parameters using reinforcement learning models.
It improves the reliability and accuracy of the traction strategy, reduces the inaccuracy caused by the subjective awareness of medical staff, ensures the safety and effectiveness of orthopedic traction for children, and avoids physical damage to the patient.
Smart Images

Figure CN118948514A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of medical devices, and in particular to a control method and system for a pediatric orthopedic traction auxiliary tool. Background Art
[0002] Traction utilizes the principle of action and reaction in mechanics, acting on the affected limb through the pull of gravity, relieving the tension and retraction of the soft tissue at the fracture and dislocation site, thereby reducing the fracture or dislocation and achieving the purpose of treatment.
[0003] Before traction treatment is performed on patients, it is necessary to determine the traction strategy (such as traction strength, traction angle, and traction duration, etc.). At present, the traction strategy is determined by medical staff based on the patient's symptoms, which is highly subjective. Due to the different physical conditions and tolerance of different patients, the reliability and accuracy of the determined traction strategy are low. This will result in poor treatment effects and even damage to the patient's body. Especially for children, it is easy to cause physical pain and cause restlessness, which will cause secondary damage to the diseased area. Summary of the invention
[0004] The present application provides a control method and system for a pediatric orthopedic traction auxiliary tool, which are used to solve the problems of low reliability and low accuracy of traction strategies determined in the prior art.
[0005] In the first aspect, the present application provides a control method for a pediatric orthopedic traction auxiliary tool, which is applied to a control system of a pediatric orthopedic traction auxiliary tool. The control system of the pediatric orthopedic traction auxiliary tool includes a bed for a child to lie down, an electric traction assembly and a human-computer interaction module arranged on the bed, and a main processor and a communication module embedded in the bed. The main processor is electrically connected to the human-computer interaction module, the communication module and the human-computer interaction module respectively. The method provided by the present application includes:
[0006] The communication module receives disease description information and patient characteristic information associated with orthopedic diseases from the medical terminal device, wherein the disease description information includes the name of the disease, the severity of the disease, and the body part where the disease occurs, and the patient characteristic information includes at least the patient's age, height, weight, and gender;
[0007] The main processor inputs the condition description information and the patient characteristic information into the pre-trained traction parameter determination model to determine a plurality of first traction strategies having a time sequence relationship, wherein the first traction strategy corresponding to each time sequence at least includes a first traction strength, a first traction angle, and a first traction duration, and the traction parameter determination model is obtained by inputting a plurality of training samples into the to-be-trained network for training, and each training sample includes historical condition description information, corresponding historical patient characteristic information, and corresponding historical first traction strategy;
[0008] The human-computer interaction module receives a second traction strategy having a time sequence relationship input by a medical staff, where the second traction strategy at least includes a second traction force, a second traction angle, and a second traction duration;
[0009] For the same timing, the main processor determines the final traction force according to the first traction force and the second traction force, determines the final traction angle according to the first traction angle and the second traction angle, and determines the final traction duration according to the first traction duration and the second traction duration, so as to obtain multiple final traction strategies with a timing relationship;
[0010] The main processor controls the electric traction component to perform traction operations on the patient's diseased body part according to the timing of multiple final traction strategies, the final traction strength, the final traction angle and the final traction duration corresponding to each final traction strategy.
[0011] In a possible implementation, the control system of the pediatric orthopedic traction auxiliary tool further includes a wearable device, the wearable device includes a surface electromyography sensor, an ultrasonic transceiver module, and a pressure sensor, and the main processor is electrically connected to the surface electromyography sensor, the ultrasonic transceiver module, and the pressure sensor, respectively. The method provided in the present application includes:
[0012] The surface electromyography sensor collects electromyography signals of the body part where the disease occurs, the ultrasonic transceiver module collects ultrasonic images of the body part where the disease occurs, and the pressure sensor detects the resistance force signal of the patient against the traction force of the electric traction component;
[0013] The main processor extracts the electromyographic feature vector from the electromyographic signal, the soft tissue feature vector from the ultrasonic image, and the resistance force feature vector from the resistance force signal;
[0014] The main processor combines the myoelectric feature vector, the soft tissue feature vector and the resistance feature vector to obtain the human body feedback feature vector;
[0015] Determine the similarity difference between the human body feedback feature vector and the standard human body feedback feature vector. When the similarity difference is greater than the set difference threshold, use the reinforcement learning model to update the network parameters of the traction parameter determination model according to the human body feedback feature vector and the similarity difference; and return to the execution main processor to input the condition description information and the patient characteristic information into the pre-trained traction parameter determination model to determine the steps of multiple first traction strategies with a time sequence relationship until the similarity difference is less than the set difference threshold.
[0016] In a possible implementation, the control system of the pediatric orthopedic traction auxiliary tool further includes a wearable device, the wearable device includes a surface electromyography sensor and a pressure sensor, the main processor is electrically connected to the surface electromyography sensor and the pressure sensor, respectively, and the method provided in the present application includes:
[0017] The surface electromyographic sensor collects electromyographic signals of the body part where the disease occurs, and the pressure sensor detects the resistance force of the patient against the traction force of the electric traction component;
[0018] When the main processor detects that the electromyographic signal is abnormal or the resistance force is greater than the set resistance force threshold, it controls the electric traction component to stop performing the traction operation on the patient's body part where the disease occurs.
[0019] In a possible implementation, for the same timing, the main processor determines the final traction force based on the first traction force and the second traction force, determines the final traction angle based on the first traction angle and the second traction angle, and determines the final traction duration based on the first traction duration and the second traction duration, so as to obtain multiple final traction strategies with a timing relationship.
[0020] In a possible implementation, before the communication module receives the condition description information and patient characteristic information associated with the orthopedic disease from the medical terminal device, the method provided by the present application further includes:
[0021] Input multiple training samples into the network to be trained to obtain a traction parameter determination model.
[0022] In the second aspect, the present application also provides a control system for a pediatric orthopedic traction auxiliary tool, including a bed for a child to lie down, an electric traction component and a human-computer interaction module arranged on the bed, a main processor and a communication module embedded in the bed, the main processor is electrically connected to the human-computer interaction module, the communication module and the human-computer interaction module respectively, wherein:
[0023] A communication module, used to receive disease description information and patient characteristic information associated with orthopedic diseases from a medical terminal device, wherein the disease description information includes the name of the disease, the severity of the disease, and the body part where the disease occurs, and the patient characteristic information includes at least the patient's age, height, weight, and gender;
[0024] A main processor is used to input the condition description information and the patient characteristic information into a pre-trained traction parameter determination model to determine a plurality of first traction strategies having a time sequence relationship, wherein the first traction strategy corresponding to each time sequence at least includes a first traction strength, a first traction angle, and a first traction duration, and the traction parameter determination model is obtained by inputting a plurality of training samples into a network to be trained, and each training sample includes historical condition description information, corresponding historical patient characteristic information, and corresponding historical first traction strategy;
[0025] A human-computer interaction module, configured to receive a second traction strategy having a time sequence relationship input by a medical staff, wherein the second traction strategy at least includes a second traction force, a second traction angle, and a second traction duration;
[0026] The main processor is further configured to determine, for the same time sequence, a final traction force according to the first traction force and the second traction force, a final traction angle according to the first traction angle and the second traction angle, and a final traction duration according to the first traction duration and the second traction duration, so as to obtain a plurality of final traction strategies having a time sequence relationship;
[0027] According to the timing of multiple final traction strategies, the final traction force, the final traction angle and the final traction duration corresponding to each final traction strategy, the electric traction component is controlled to perform traction operation on the patient's body part where the disease occurs.
[0028] In a possible implementation, the control system of the pediatric orthopedic traction auxiliary tool further includes a wearable device, the wearable device includes a surface electromyography sensor, an ultrasonic transceiver module, and a pressure sensor, and the main processor is electrically connected to the surface electromyography sensor, the ultrasonic transceiver module, and the pressure sensor, respectively.
[0029] A surface electromyography sensor for collecting electromyography signals of a body part where a disease occurs, an ultrasonic transceiver module for collecting ultrasonic images of a body part where a disease occurs, and a pressure sensor for detecting a resistance force signal of a patient against the traction force of an electric traction component;
[0030] A main processor, used for extracting an electromyographic feature vector from the electromyographic signal, extracting a soft tissue feature vector from the ultrasonic image, and extracting an antagonistic force feature vector from the antagonistic force signal;
[0031] The myoelectric feature vector, the soft tissue feature vector and the resistance feature vector are spliced to obtain the human body feedback feature vector;
[0032] Determine the similarity difference between the human body feedback feature vector and the standard human body feedback feature vector. When the similarity difference is greater than the set difference threshold, use the reinforcement learning model to update the network parameters of the traction parameter determination model according to the human body feedback feature vector and the similarity difference; and return to the execution main processor to input the condition description information and the patient characteristic information into the pre-trained traction parameter determination model to determine the steps of multiple first traction strategies with a time sequence relationship until the similarity difference is less than the set difference threshold.
[0033] In a possible implementation, the control system of the pediatric orthopedic traction auxiliary tool further includes a wearable device, the wearable device includes a surface electromyography sensor and a pressure sensor, and the main processor is electrically connected to the surface electromyography sensor and the pressure sensor, respectively.
[0034] A surface electromyographic sensor for collecting electromyographic signals of a body part where a disease occurs, and a pressure sensor for detecting the resistance of a patient against the traction force of an electric traction assembly;
[0035] The main processor is also used to control the electric traction component to stop performing traction operations on the patient's body part where the disease occurs when an abnormality in the electromyographic signal is detected or the resistance force is greater than a set resistance force threshold.
[0036] In a possible implementation manner, the main processor is further configured to input a plurality of training samples into the network to be trained to obtain a traction parameter determination model.
[0037] The present application provides a control method and system for a pediatric orthopedic traction auxiliary tool. The main processor inputs the condition description information and patient characteristic information into a pre-trained traction parameter determination model to determine multiple first traction strategies with a time sequence relationship. Since the traction parameter determination model is obtained by inputting multiple training samples into a network to be trained, and each training sample includes historical condition description information, corresponding historical patient characteristic information, and corresponding historical first traction strategy, it can be seen that the determination of the first traction strategy is separated from the subjective consciousness of medical staff and has high reliability. Furthermore, the human-computer interaction module receives the second traction strategy with a time sequence relationship input by the medical staff. It can be understood that the second traction strategy is separated from the inaccuracy caused by the training error of the traction parameter determination model.
[0038] For the same timing, the main processor determines the final traction force based on the first traction force and the second traction force, determines the final traction angle based on the first traction angle and the second traction angle, and determines the final traction duration based on the first traction duration and the second traction duration, so as to obtain multiple final traction strategies with a timing relationship.
[0039] It can be seen that the final traction strategy not only considers the first traction strategy output by the traction parameter determination model, but also considers the second traction strategy input by the medical staff, reducing the inaccuracy caused by the training error of the traction parameter determination model and the inaccuracy caused by the subjective consciousness of the medical staff, and thus the reliability of the multiple final traction strategies with a time sequence relationship is high. Especially for children, it will not cause damage to the child's body parts. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0041] Figure 1 A schematic diagram of the structure of a control system of a pediatric orthopedic traction auxiliary tool provided in an embodiment of the present application;
[0042] Figure 2 This is a flow chart of a control method for a pediatric orthopedic traction assisting tool provided in an embodiment of the present application. DETAILED DESCRIPTION
[0043] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments made by ordinary technicians in this field under the enlightenment of the embodiments belong to the scope of protection of the present application.
[0044] The present application embodiment provides a control method for a pediatric orthopedic traction auxiliary tool, which is applied to a control system of a pediatric orthopedic traction auxiliary tool. Figure 1 As shown, the control system of the pediatric orthopedic traction assisting tool includes a bed 106 for children to lie down, an electric traction component 103 and a human-computer interaction module 104 arranged on the bed 106, and a main processor 101 and a communication module 102 embedded in the bed 106. The main processor 101 is electrically connected to the human-computer interaction module 104, the communication module 102 and the human-computer interaction module 104 respectively. Among them, the electric traction component 103 may include a driving motor, a traction weight, a pulley, a lead, and a belt. The traction weight, the lead and the belt are connected in sequence, and the lead is slidably connected to the pulley. The driving motor is used to drive the traction weight to pull the belt, and the belt can be put on the body part where the disease occurs (such as the knee, neck, etc.). Figure 2 As shown, the method provided in the embodiment of the present application includes:
[0045] S201: The communication module 102 receives disease description information and patient characteristic information associated with orthopedic diseases from a medical terminal device.
[0046] The disease description information includes the disease name, disease severity, and body part where the disease occurs. The patient characteristic information includes at least the patient's age, height, weight, and gender.
[0047] For example, the name of the disease is "knee fracture", the severity of the disease is "mild", the body part where the disease occurs is (knee), the patient's age is "11 years old", height (148 cm), weight (35 kg), and gender (male).
[0048] S202: The main processor 101 inputs the condition description information and the patient characteristic information into the pre-trained traction parameter determination model to determine a plurality of first traction strategies having a time sequence relationship.
[0049] The first traction strategy corresponding to each time sequence at least includes a first traction strength, a first traction angle, and a first traction duration. The traction parameter determination model is obtained by inputting multiple training samples into the network to be trained, and each training sample includes historical condition description information, corresponding historical patient feature information, and corresponding historical first traction strategy. For example, before S201, multiple training samples are input into the network to be trained to obtain the traction parameter determination model.
[0050] Such as the first traction force (20N), the first traction angle (30 degrees upward with the horizontal plane) and the first traction duration (10min).
[0051] S203: The human-computer interaction module 104 receives a second traction strategy having a time sequence relationship input by the medical staff, where the second traction strategy at least includes a second traction force, a second traction angle, and a second traction duration.
[0052] Such as the first traction force (18N), the first traction angle (35 degrees upward with the horizontal plane) and the first traction duration (9min).
[0053] Exemplarily, the main processor 101 determines the final traction force according to the formula F3=a1F1+a2F2, where F3 is the final traction force, F1 is the first traction force, and F2 is the second traction force; determines the final traction angle according to the formula θ3=a1θ1+a2θ2, where θ3 is the final traction force, θ1 is the first traction force, and θ2 is the second traction force; determines the final traction duration according to T3=a1T1+a2T2, where T3 is the final traction force, T1 is the first traction force, and T2 is the second traction force. Wherein, a1 can be equal to 0.6, and a2 can be equal to 0.4.
[0054] S204: For the same timing, the main processor 101 determines the final traction force according to the first traction force and the second traction force, determines the final traction angle according to the first traction angle and the second traction angle, and determines the final traction duration according to the first traction duration and the second traction duration, so as to obtain multiple final traction strategies with a timing relationship.
[0055] S205: The main processor 101 controls the electric traction component 103 to perform traction operations on the patient's body part where the disease occurs according to the timing of multiple final traction strategies, the final traction force, the final traction angle and the final traction duration corresponding to each final traction strategy.
[0056] In summary, in a control method for a pediatric orthopedic traction auxiliary tool provided in an embodiment of the present application, the main processor 101 inputs the condition description information and the patient characteristic information into a pre-trained traction parameter determination model to determine multiple first traction strategies with a time sequence relationship. Since the traction parameter determination model is obtained by inputting multiple training samples into the network to be trained, and each training sample includes historical condition description information, corresponding historical patient characteristic information, and corresponding historical first traction strategy, it can be seen that the determination of the first traction strategy is separated from the subjective consciousness of medical staff and has high reliability. Furthermore, the human-computer interaction module 104 receives the second traction strategy with a time sequence relationship input by the medical staff. It can be understood that the second traction strategy is separated from the inaccuracy caused by the training error of the traction parameter determination model.
[0057] For the same timing, the main processor 101 determines the final traction force based on the first traction force and the second traction force, determines the final traction angle based on the first traction angle and the second traction angle, and determines the final traction duration based on the first traction duration and the second traction duration, so as to obtain multiple final traction strategies with a timing relationship.
[0058] It can be seen that the final traction strategy not only considers the first traction strategy output by the traction parameter determination model, but also considers the second traction strategy input by the medical staff, reducing the inaccuracy caused by the training error of the traction parameter determination model and the inaccuracy caused by the subjective consciousness of the medical staff, and thus the reliability of the multiple final traction strategies with a time sequence relationship is high. Especially for children, it will not cause damage to the child's body parts.
[0059] In addition, the control system of the pediatric orthopedic traction auxiliary tool also includes a wearable device 105, which includes a surface electromyography sensor, an ultrasonic transceiver module, and a pressure sensor. The main processor 101 is electrically connected to the surface electromyography sensor, the ultrasonic transceiver module, and the pressure sensor, respectively. The method provided in the embodiment of the present application may also include:
[0060] Step 1: The surface electromyography sensor collects electromyography signals of the body part where the disease occurs, the ultrasonic transceiver module collects ultrasonic images of the body part where the disease occurs, and the pressure sensor detects the resistance force signal of the patient against the traction force of the electric traction component 103.
[0061] Understandably, when the final traction strategy does not meet the patient's current tolerance, it may cause muscle spasms, soft tissue tension or even strain, and the patient (especially children) may resist the traction force to avoid pain. Therefore, it is necessary to collect electromyographic signals, ultrasonic images and resistance signals.
[0062] Step 2: The main processor 101 extracts the myoelectric feature vector from the myoelectric signal, extracts the soft tissue feature vector from the ultrasonic image, and extracts the resistance feature vector from the resistance signal.
[0063] Step 3: The main processor 101 concatenates the myoelectric feature vector, the soft tissue feature vector, and the resistance feature vector to obtain a human body feedback feature vector.
[0064] Step 4: Determine the similarity difference between the human body feedback feature vector and the standard human body feedback feature vector. When the similarity difference is greater than the set difference threshold, use the reinforcement learning model to update the network parameters of the traction parameter determination model according to the human body feedback feature vector and the similarity difference; and return to execute the main processor 101 to input the condition description information and the patient characteristic information into the pre-trained traction parameter determination model, and determine the steps of multiple first traction strategies with a time sequence relationship, until the similarity difference is less than the set difference threshold.
[0065] Based on the above steps 1 to 4, it can be known that when the difference between the human body feedback feature vector and the standard human body feedback feature vector is greater than the set difference threshold, the reliability of the above-determined multiple final traction strategies is low. Therefore, the reinforcement learning model is used to optimize the traction parameter determination model network parameters according to the human body feedback feature vector and the similarity difference, so as to determine a more accurate first traction strategy, and then determine a more accurate final traction strategy with high reliability.
[0066] In another possible implementation, the control system of the pediatric orthopedic traction auxiliary tool further includes a wearable device 105, the wearable device 105 includes a surface electromyography sensor and a pressure sensor, the main processor 101 is electrically connected to the surface electromyography sensor and the pressure sensor, respectively, and the method provided in the embodiment of the present application includes:
[0067] Step A: The surface electromyography sensor collects electromyography signals of the body part where the disease occurs, and the pressure sensor detects the resistance force of the patient against the traction force of the electric traction component 103.
[0068] Understandably, when the final traction strategy does not meet the patient's current tolerance, it may cause muscle spasms, soft tissue tension or even strain, and the patient (especially children) may resist the traction force to avoid pain. Therefore, it is necessary to collect electromyographic signals, ultrasonic images and resistance signals.
[0069] Step B: When the main processor 101 detects that the electromyographic signal is abnormal or the resistance force is greater than the set resistance force threshold, it controls the electric traction component 103 to stop performing the traction operation on the patient's body part where the disease occurs.
[0070] Based on the above steps A and B, it is possible to avoid situations in which muscle spasms, high tension on soft tissues or even strains are caused, and patients (especially children) resist the pulling force to avoid pain.
[0071] Still see Figure 1 The embodiment of the present application also provides a control system for a pediatric orthopedic traction auxiliary tool, including a bed 106 for a child to lie down, an electric traction component 103 and a human-computer interaction module 104 arranged on the bed 106, a main processor 101 and a communication module 102 embedded in the bed 106, the main processor 101 is electrically connected to the human-computer interaction module 104, the communication module 102 and the human-computer interaction module 104, respectively, wherein,
[0072] The communication module 102 is used to receive disease description information and patient characteristic information associated with orthopedic diseases from a medical terminal device, wherein the disease description information includes the name of the disease, the severity of the disease, and the body part where the disease occurs, and the patient characteristic information includes at least the patient's age, height, weight, and gender;
[0073] The main processor 101 is used to input the condition description information and the patient characteristic information into the pre-trained traction parameter determination model to determine a plurality of first traction strategies having a time sequence relationship, wherein the first traction strategy corresponding to each time sequence at least includes a first traction strength, a first traction angle and a first traction duration, and the traction parameter determination model is obtained by inputting a plurality of training samples into the to-be-trained network for training, and each training sample includes historical condition description information, corresponding historical patient characteristic information and corresponding historical first traction strategy;
[0074] The human-computer interaction module 104 is used to receive a second traction strategy with a time sequence relationship input by a medical staff, where the second traction strategy at least includes a second traction force, a second traction angle, and a second traction duration;
[0075] The main processor 101 is further configured to determine, for the same time sequence, a final traction force according to the first traction force and the second traction force, a final traction angle according to the first traction angle and the second traction angle, and a final traction duration according to the first traction duration and the second traction duration, so as to obtain a plurality of final traction strategies having a time sequence relationship;
[0076] According to the timing of the multiple final traction strategies, the final traction strength, the final traction angle and the final traction duration corresponding to each final traction strategy, the electric traction component 103 is controlled to perform traction operation on the patient's body part where the disease occurs.
[0077] In a possible implementation, the control system of the pediatric orthopedic traction auxiliary tool further includes a wearable device 105, the wearable device 105 includes a surface electromyography sensor, an ultrasonic transceiver module, and a pressure sensor, and the main processor 101 is electrically connected to the surface electromyography sensor, the ultrasonic transceiver module, and the pressure sensor, respectively.
[0078] A surface electromyography sensor for collecting electromyography signals of a body part where a disease occurs, an ultrasonic transceiver module for collecting ultrasonic images of a body part where a disease occurs, and a pressure sensor for detecting a resistance force signal of a patient against the traction force of the electric traction assembly 103;
[0079] A main processor 101, configured to extract an electromyographic feature vector from an electromyographic signal, extract a soft tissue feature vector from an ultrasonic image, and extract an antagonistic force feature vector from an antagonistic force signal;
[0080] The myoelectric feature vector, the soft tissue feature vector and the resistance feature vector are spliced to obtain the human body feedback feature vector;
[0081] Determine the similarity difference between the human body feedback feature vector and the standard human body feedback feature vector. When the similarity difference is greater than the set difference threshold, use the reinforcement learning model to update the network parameters of the traction parameter determination model according to the human body feedback feature vector and the similarity difference; and return to execute the main processor 101 to input the condition description information and the patient characteristic information into the pre-trained traction parameter determination model to determine the steps of multiple first traction strategies with a time sequence relationship, until the similarity difference is less than the set difference threshold.
[0082] In a possible implementation, the control system of the pediatric orthopedic traction auxiliary tool further includes a wearable device 105, the wearable device 105 includes a surface electromyography sensor and a pressure sensor, and the main processor 101 is electrically connected to the surface electromyography sensor and the pressure sensor, respectively.
[0083] A surface electromyography sensor for collecting electromyography signals of a body part where a disease occurs, and a pressure sensor for detecting the resistance of the patient against the traction force of the electric traction assembly 103;
[0084] The main processor 101 is also used to control the electric traction component 103 to stop performing traction operations on the patient's body part where the disease occurs when an abnormality in the electromyographic signal is detected or the resistance force is greater than a set resistance force threshold.
[0085] In a possible implementation, the main processor 101 is specifically configured to determine the final traction force according to the formula F3=a1F1+a2F2, where F3 is the final traction force, F1 is the first traction force, and F2 is the second traction force;
[0086] According to the formula θ3=a1θ1+a2θ2, the final traction angle is determined, where θ3 is the final traction force, θ1 is the first traction force, and θ2 is the second traction force;
[0087] The final traction duration is determined according to T3=a1T1+a2T2, wherein T3 is the final traction force, T1 is the first traction force, T2 is the second traction force, a1 is the first weighting coefficient, and a2 is the second weighting coefficient.
[0088] In a possible implementation manner, the main processor 101 is further configured to input a plurality of training samples into the network to be trained to obtain a traction parameter determination model.
[0089] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.
Claims
1. A control method for a pediatric orthopedic traction auxiliary tool, characterized in that: A control system for a pediatric orthopedic traction auxiliary tool, the control system of the pediatric orthopedic traction auxiliary tool comprising a bed for a child to lie down, an electric traction assembly and a human-computer interaction module arranged on the bed, a main processor and a communication module embedded in the bed, the main processor being electrically connected to the human-computer interaction module, the communication module and the human-computer interaction module respectively, the method comprising: The communication module receives disease description information and patient characteristic information associated with orthopedic diseases from the medical terminal device, wherein the disease description information includes the name of the disease, the severity of the disease, and the body part where the disease occurs, and the patient characteristic information includes at least the patient's age, height, weight, and gender; The main processor inputs the condition description information and the patient characteristic information into a pre-trained traction parameter determination model to determine a plurality of first traction strategies having a time sequence relationship, wherein the first traction strategy corresponding to each time sequence at least includes a first traction strength, a first traction angle, and a first traction duration, and the traction parameter determination model is obtained by inputting a plurality of training samples into a network to be trained, and each of the training samples includes historical condition description information, corresponding historical patient characteristic information, and corresponding historical first traction strategy; The human-computer interaction module receives a second traction strategy having a time sequence relationship input by a medical staff, wherein the second traction strategy at least includes a second traction force, a second traction angle, and a second traction duration; For the same time sequence, the main processor determines a final traction force according to the first traction force and the second traction force, determines a final traction angle according to the first traction angle and the second traction angle, and determines a final traction duration according to the first traction duration and the second traction duration, so as to obtain a plurality of final traction strategies having a time sequence relationship; The main processor controls the electric traction component to perform traction operations on the patient's diseased body part according to the timing of the multiple final traction strategies, the final traction force, the final traction angle and the final traction duration corresponding to each final traction strategy.
2. The method according to claim 1, characterized in that The control system of the pediatric orthopedic traction auxiliary tool also includes a wearable device, the wearable device includes a surface electromyography sensor, an ultrasonic transceiver module and a pressure sensor, the main processor is electrically connected to the surface electromyography sensor, the ultrasonic transceiver module and the pressure sensor respectively, and the method includes: The surface electromyography sensor collects electromyography signals of the body part where the disease occurs, the ultrasonic transceiver module collects ultrasonic images of the body part where the disease occurs, and the pressure sensor detects the resistance force signal of the patient against the traction force of the electric traction component; The main processor extracts an electromyographic feature vector from the electromyographic signal, extracts a soft tissue feature vector from the ultrasonic image, and extracts an antagonistic force feature vector from the antagonistic force signal; The main processor splices the myoelectric feature vector, the soft tissue feature vector and the resistance feature vector to obtain a human body feedback feature vector; Determine the similarity difference between the human body feedback feature vector and the standard human body feedback feature vector. When the similarity difference is greater than a set difference threshold, use the reinforcement learning model to update the network parameters of the traction parameter determination model according to the human body feedback feature vector and the similarity difference; and return to execute the main processor to input the condition description information and the patient characteristic information into the pre-trained traction parameter determination model to determine the steps of multiple first traction strategies with a time sequence relationship, until the similarity difference is less than the set difference threshold.
3. The method according to claim 1, characterized in that The control system of the pediatric orthopedic traction auxiliary tool also includes a wearable device, the wearable device includes a surface electromyography sensor and a pressure sensor, the main processor is electrically connected to the surface electromyography sensor and the pressure sensor respectively, and the method includes: The surface electromyography sensor collects electromyography signals of the body part where the disease occurs, and the pressure sensor detects the resistance force of the patient against the traction force of the electric traction component; When the main processor detects that the electromyographic signal is abnormal or the resistance force is greater than a set resistance force threshold, the main processor controls the electric traction component to stop performing the traction operation on the patient's body part where the disease occurs.
4. The method according to claim 1, characterized in that: For the same timing, the main processor determines the final traction force according to the first traction force and the second traction force, determines the final traction angle according to the first traction angle and the second traction angle, and determines the final traction duration according to the first traction duration and the second traction duration, so as to obtain multiple final traction strategies with a timing relationship.
5. The method according to claim 1, characterized in that Before the communication module receives the condition description information and patient characteristic information associated with the orthopedic disease from the medical terminal device, the method further includes: A plurality of the training samples are input into the network to be trained to obtain the traction parameter determination model.
6. A control system for a pediatric orthopedic traction auxiliary tool, characterized in that: The invention comprises a bed for children to lie down, an electric traction assembly and a human-computer interaction module arranged on the bed, a main processor and a communication module embedded in the bed, wherein the main processor is electrically connected to the human-computer interaction module, the communication module and the human-computer interaction module respectively, wherein: The communication module is used to receive disease description information and patient characteristic information associated with orthopedic diseases from a medical terminal device, wherein the disease description information includes the name of the disease, the severity of the disease, and the body part where the disease occurs, and the patient characteristic information includes at least the patient's age, height, weight, and gender; The main processor is used to input the condition description information and the patient characteristic information into a pre-trained traction parameter determination model to determine a plurality of first traction strategies having a time sequence relationship, wherein the first traction strategy corresponding to each time sequence at least includes a first traction strength, a first traction angle, and a first traction duration, and the traction parameter determination model is obtained by inputting a plurality of training samples into a network to be trained, and each of the training samples includes historical condition description information, corresponding historical patient characteristic information, and corresponding historical first traction strategy; The human-computer interaction module is used to receive a second traction strategy with a time sequence relationship input by a medical staff, wherein the second traction strategy at least includes a second traction force, a second traction angle, and a second traction duration; The main processor is also used for determining, for the same timing, a final traction force according to the first traction force and the second traction force, a final traction angle according to the first traction angle and the second traction angle, and a final traction duration according to the first traction duration and the second traction duration, so as to obtain a plurality of final traction strategies having a timing relationship; and controlling the electric traction assembly to perform a traction operation on the patient's body part where the disease occurs according to the timing of the plurality of final traction strategies, the final traction force, the final traction angle, and the final traction duration corresponding to each final traction strategy.
7. The system according to claim 6, characterized in that The control system of the pediatric orthopedic traction auxiliary tool also includes a wearable device, which includes a surface electromyography sensor, an ultrasonic transceiver module, and a pressure sensor. The main processor is electrically connected to the surface electromyography sensor, the ultrasonic transceiver module, and the pressure sensor, respectively. The surface electromyography sensor is used to collect electromyography signals of the body part where the disease occurs, the ultrasonic transceiver module is used to collect ultrasonic images of the body part where the disease occurs, and the pressure sensor is used to detect the resistance force signal of the patient against the traction force of the electric traction component; The main processor is used to extract the electromyographic feature vector from the electromyographic signal, extract the soft tissue feature vector from the ultrasonic image, and extract the resistance feature vector from the resistance signal; The myoelectric feature vector, the soft tissue feature vector and the resistance feature vector are spliced to obtain a human body feedback feature vector; Determine a similarity difference between a human body feedback feature vector and a standard human body feedback feature vector, and when the similarity difference is greater than a set difference threshold, use a reinforcement learning model to update a network parameter of the traction parameter determination model according to the human body feedback feature vector and the similarity difference; And return to execute the main processor to input the condition description information and patient characteristic information into the pre-trained traction parameter determination model, and determine the steps of multiple first traction strategies with a time sequence relationship, until the similarity difference is less than the set difference threshold.
8. The system according to claim 6, characterized in that The control system of the pediatric orthopedic traction auxiliary tool further includes a wearable device, wherein the wearable device includes a surface electromyography sensor and a pressure sensor, and the main processor is electrically connected to the surface electromyography sensor and the pressure sensor respectively. The surface electromyography sensor is used to collect electromyography signals of the body part where the disease occurs, and the pressure sensor is used to detect the resistance force of the patient against the traction force of the electric traction component; The main processor is also used to control the electric traction component to stop performing traction operations on the patient's body part where the disease occurs when it is detected that the electromyographic signal is abnormal or the resistance force is greater than a set resistance force threshold.
9. The system according to claim 6, characterized in thatThe main processor is also used to input the plurality of training samples into the network to be trained for training, so as to obtain the traction parameter determination model.
Citation Information
Cited By
Traction bed adjusting method, device and equipment and storage medium
CN119344938A
A traction table adjustment method, apparatus, device, and storage medium
CN119344938B
