An orthopedic traction assisting method and system based on artificial intelligence

Abstract

The application discloses an orthopedic traction auxiliary method and system based on artificial intelligence, relates to the technical field of orthopedic traction, and first acquires the image of the fracture of a patient, and establishes a three-dimensional bone model; secondly, according to the fracture type, past medical history and information of each traction device of the patient, the traction device used is acquired; then, according to the running force points, tendon distribution and pressure distribution at the bottom of the traction device of the fracture of the patient, the installation position of the traction device is determined; finally, according to the age, weight, fracture position and past medical history of the patient, each standby traction scheme is selected, the tolerance coefficient of the patient to the traction angle and traction degree in each standby traction scheme is analyzed, and the final traction scheme of the patient is determined according to the analysis result, so that the traction device meets the use demand of the patient and the installation position meets the installation requirement, and the accuracy of installation and the effectiveness of traction are also ensured.

Description

Technical Field

[0001] This invention relates to the field of orthopedic traction technology, specifically to an orthopedic traction assistance method and system based on artificial intelligence. Background Technology

[0002] Orthopedic traction is an important means of treating fractures, dislocations and other diseases. With the development of artificial intelligence technology, its application in the field of orthopedic traction can effectively improve the accuracy of traction and the treatment effect, and provide patients with better medical services.

[0003] Existing technology, such as application CN115634090A, discloses an artificial intelligence-based orthopedic traction assistance method and system. This system collects sample images of healthy limbs and sample image data of the affected limb at various times during the recovery phase. Based on the sample image data of the affected limb, it selects a stretching method. Through analysis of the sample image data of the affected limb, it moves the orthopedic traction device according to the direction of the analysis results. After adjustment, the orthopedic traction device is fixed, facilitating adjustment of the appropriate spacing of the orthopedic traction device according to the position of the affected limb. The system detects the pressure data of the orthopedic traction device and transmits it to a data processor. The data processor determines whether the tension of the pull rope meets the requirements based on the set tension value.

[0004] Regarding the above solutions, the applicant of this invention has found that the above technology has at least the following technical problems: 1. The existing technology selects traction devices based on sample images of healthy limbs and sample images of patients' affected limbs. It lacks analysis of whether the patient's past medical history is suitable for each traction device, and does not determine whether the price of the traction device is within the range that the patient can afford, thus failing to ensure that the traction device meets the patient's usage needs.

[0005] 2. Existing technology adjusts the installation of the traction device based on the analysis results of the patient's limb sample images. However, the adjustment process lacks analysis of the pressure distribution at the bottom of the traction device and the impact of the traction device on surrounding tissues, which cannot guarantee that the installation position of the traction device meets the installation requirements.

[0006] 3. Existing technologies only analyze the traction force when developing traction plans, lacking analysis of the traction angle and the patient's tolerance to the traction angle and force, thus failing to guarantee the effectiveness of traction. Summary of the Invention

[0007] In view of the above-mentioned technical deficiencies, the purpose of this invention is to provide an orthopedic traction assistance method and system based on artificial intelligence.

[0008] To solve the above-mentioned technical problems, the present invention adopts the following technical solution: In the first aspect, the present invention provides an orthopedic traction assistance method based on artificial intelligence, including the following steps: Step 1, data acquisition: using medical imaging equipment to acquire images of the patient's fracture site and establish a three-dimensional skeletal model of the patient.

[0009] Step 2: Determine the traction device: Obtain the patient's fracture type, past medical history, and information on each traction device. Analyze the availability coefficient of each traction device, and select the traction device for the patient based on the availability coefficient and the cost of each traction device.

[0010] Step 3: Determine the installation location of the traction device: Plan the installation area of ​​the traction device, and set each installation point in the installation area according to the preset first distance threshold. Obtain the location of each force point of the fracture site, analyze the influence index of each installation point on the patient's movement, and select each backup installation point. Based on the tendon distribution of each backup installation point and the bottom pressure distribution of the traction device at each backup installation point, analyze the installation coefficient of each backup installation point, compare them, and select the backup installation point with the highest installation coefficient as the installation location of the traction device.

[0011] Step 4: Determine the traction plan: Obtain the patient's age, weight, fracture location, and past medical history, and retrieve all alternative traction plans from the database. Based on the traction force and traction angle of each alternative traction plan, determine the patient's final traction plan.

[0012] Preferably, the process of determining the traction device is as follows: The patient's fracture type, past medical history, and information on each traction device are retrieved from the database. The availability coefficient of each traction device is analyzed. If the availability coefficient of a traction device is 1, it means that the traction device meets the patient's needs. If the availability coefficient of a traction device is 0, it means that the traction device does not meet the patient's needs. This method is used to determine whether each traction device meets the patient's needs, and each traction device that meets the patient's needs is selected as a backup traction device. The required cost of each backup traction device is retrieved from the database and compared with the patient's affordable budget. Backup traction devices whose costs are within the patient's affordable budget are selected as the traction devices to be used. The required costs of each traction device are compared, and the traction device with the lowest required cost is selected as the traction device used by the patient.

[0013] Preferably, the analysis of the availability coefficient of each traction device is carried out as follows: The patient's fracture type, past medical history, and characteristics of each traction device are obtained from the database and input into the fracture type model and past medical history model, and the fracture type conformity value of each traction device is output. Consistency value with past medical history ,but: In the formula This represents the preset coefficient threshold. Representing the Availability coefficient of each traction device Represents the number of each traction device. =1,2,3,..., , Represents the total number of traction devices. and All are positive integers.

[0014] Preferably, the specific process for determining the installation location of the traction device is as follows: S11, obtain the patient's fracture location, fracture type, and traction device, and obtain the fracture location, fracture type, and traction device of each historical patient from the database. Compare the fracture location, fracture type, and traction device of each historical patient with the fracture location, fracture type, and traction device of the current patient. If the fracture location, fracture type, and traction device of a certain historical patient are all the same as those of the current patient, then obtain the installation location of the traction device of that historical patient and call this installation location the historical installation location. Obtain each historical installation location of the traction device in this way, and cluster each historical installation location to obtain the installation area of ​​the traction device.

[0015] S12. Within the installation area, each installation point is set according to a preset first distance threshold, and the positions of each force exertion point at the patient's fracture site are obtained. Based on the positions of each force exertion point and each installation point, the influence index of the installation point on the patient's movement is analyzed. If the influence index of a certain installation point on the patient's movement is 1, it means that the installation point affects the patient's movement. If the influence index of a certain installation point on the patient's movement is 0, it means that the installation point does not affect the patient's movement. This method is used to determine whether each installation point affects the patient's movement, and each installation point that does not affect the patient's movement is called a backup installation point.

[0016] S13. At the bottom of the traction device, set up each collection point according to the preset second distance threshold, install pressure sensors at each collection point, simulate the installation of each backup installation point on the patient's three-dimensional bone model, and collect the pressure of each collection point at the bottom of the traction device during the simulation installation process. At the same time, obtain the position of each tendon around each backup installation point, analyze the installation coefficient of each backup installation point, compare them, select the backup installation point with the highest installation coefficient, and use its position as the installation position of the traction device.

[0017] Preferably, the analysis of the impact of the installation points on the patient's movement is carried out as follows: The coordinates of each force exertion point in the patient's three-dimensional skeletal model and the coordinates of each installation point are obtained; the distance between each installation point and each force exertion point is calculated; then, based on the analysis formula: Get the first Indicators of the impact of each installation point on patient movement In the formula Representing the The installation point and its surroundings The distance between the points of force application This represents the preset third distance threshold. The number representing each installation point =1,2,3,..., , Represents the total number of installation points. Represents the total number of all points of force application. =1,2,3,..., , The total number of points of force application. , , and All are positive integers.

[0018] Preferably, the specific process of analyzing the installation coefficient of each backup installation point is as follows: S21, obtain the pressure of each collection point at the bottom of the traction device at each backup installation point and the coordinates of each tendon around each backup installation point, and calculate the distance between each backup installation point and each tendon around it.

[0019] S22. Combine each sampling point at the bottom of the traction device in pairs to obtain each combination. Calculate the pressure difference between the two sampling points in each combination, and use this difference as the difference between the combinations. Then, normalize the result according to the analysis formula: Get the first Installation coefficient of backup installation points In the formula The traction device is represented in the first The first backup installation point The difference between the combinations, Representing the The backup installation point and its surrounding area The distance between the tendons, This represents the number of each backup installation point. =1,2,3,..., , This represents the total number of backup installation points. The number representing each combination, =1,2,3,..., , Represents the total number of combinations. The numbers representing the tendons, =1,2,3,..., , Represents the total number of tendons. , , , , and All are positive integers.

[0020] Preferably, the process of obtaining the final traction plan for the patient is as follows: S31. Obtain the patient's age, weight, fracture location, fracture type, and past medical history, and compare them with the age, weight, fracture location, fracture type, and past medical history of historical patients. Analyze the return value of the physical status of historical patients and this patient. If the return value of the physical status of a historical patient and this patient is 1, it means that the physical status of the historical patient and this patient is similar. If the return value of the physical status of a historical patient and this patient is 0, it means that the physical status of the historical patient and this patient is different. Obtain the physical status return value of historical patients with a physical status return value of 1, and obtain their traction plans from the database. The traction plans of historical patients with a physical status return value of 1 are called each backup traction plan.

[0021] S32. Obtain the traction angle and traction force of each backup traction scheme and apply them to the patient's three-dimensional skeletal model. When simulating each backup scheme in the patient's three-dimensional skeletal model, monitor the vital signs and muscle data in real time, analyze the patient's tolerance coefficient to the traction angle and traction force of each backup traction scheme, calculate the difference between the patient's tolerance coefficient to the traction angle and traction force of each backup traction scheme and the optimal tolerance coefficient, compare them, and select the backup traction scheme with the smallest difference as the patient's final traction scheme.

[0022] Preferably, the analysis of historical patients and the patient's physical condition return value is performed as follows: The patient's fracture location, fracture type, and past medical history are retrieved from the database along with the fracture location, fracture type, and past medical history of historical patients. These are then input into the analysis model, and the output is the condition return value of historical patients and the current patient. The analysis is then performed according to the following formula: To obtain the historical number The patient and the patient's physical status return value. In the formula , These represent the patient's age and weight, respectively. , Representing the historical number The patient's age and weight, Representing history Each patient and the patient's condition return value , These represent the preset age difference threshold and the preset weight difference threshold, respectively. The numbers representing the patients in history, =1,2,3,..., , Represents the total number of historical patients. and All are positive integers.

[0023] Preferably, the analysis of the patient's tolerance coefficient to the traction angle and traction force in each alternative traction scheme involves the following steps: acquiring vital sign data and muscle data at each traction moment during the simulation of each alternative traction scheme in a three-dimensional skeletal model, and inputting them into the vital sign data fluctuation model and muscle data fluctuation model. Outputting the vital sign fluctuation coefficient and muscle fluctuation coefficient during the simulation of each alternative scheme in the three-dimensional skeletal model. Simultaneously, calculating the average value of each vital sign data and the average value of each muscle data, and performing normalization processing, based on the analysis formula: Obtain the patient's opinion on the first The tolerance coefficients of traction angle and traction force in the backup traction scheme In the formula This represents simulating the first in a 3D skeletal model. The backup plan is the first The average value of each vital sign data This represents simulating the first in a 3D skeletal model. The backup plan is the first The average of individual muscle data. Representing the Standard values ​​for each vital sign data point Representing the Standard values ​​for muscle data, This represents simulating the first in a 3D skeletal model. The coefficient of vital sign fluctuation in the backup plan. This represents simulating the first in a 3D skeletal model. Muscle variability coefficient in backup plans The numbers representing the backup plans, =1,2,3,..., , Represents the total number of backup plans. The numbers representing the various vital signs data. =1,2,3,..., , The total number of vital signs data. The number representing the data for each muscle. =1,2,3,..., , The total number of muscle data. , , , , and All are positive integers.

[0024] Secondly, the present invention provides an artificial intelligence-based orthopedic traction assistance system, comprising the following modules: a data acquisition module for acquiring images of the patient's fracture site using medical imaging equipment and establishing a three-dimensional skeletal model of the patient.

[0025] The traction device determination module is used to obtain the patient's fracture type, past medical history, and information on each traction device, analyze the availability coefficient of each traction device, and select the traction device for the patient based on the availability of each traction device and the cost of each traction device.

[0026] The traction device installation location determination module is used to plan the installation area of ​​the traction device, and set each installation point in the installation area according to a preset first distance threshold. It obtains the location of each force point of movement at the fracture site, analyzes the influence index of each installation point on the patient's movement, and selects each backup installation point. Based on the tendon distribution of each backup installation point and the bottom pressure distribution of the traction device at each backup installation point, it analyzes the installation coefficient of each backup installation point, compares them, and selects the backup installation point with the highest installation coefficient as the installation location of the traction device.

[0027] The traction plan determination module is used to obtain the patient's age, weight, fracture location, and past medical history, and to retrieve various backup traction plans from the database. Based on the traction force and traction angle of each backup traction plan, the final traction plan for the patient is obtained.

[0028] The database is used to store historical information about each patient, information about each traction device, the patient's fracture type, age, fracture location, and weight.

[0029] The beneficial effects of this invention are as follows: 1. This invention provides an orthopedic traction assistance method and system based on artificial intelligence. First, images of the patient's fracture site are acquired and a three-dimensional skeletal model is established. Second, based on the patient's fracture type, past medical history, and information on each traction device, the traction device to be used is acquired. Then, based on the force application points at the patient's fracture site, tendon distribution, and pressure distribution at the bottom of the traction device, the installation position of the traction device is determined. Finally, based on the patient's age, weight, fracture location, and past medical history, each backup traction scheme is selected. The patient's tolerance coefficient to the traction angle and traction force in each backup traction scheme is analyzed, and the final traction scheme for the patient is determined based on the analysis results. This ensures that the traction device meets the patient's usage needs and that the installation position meets the installation requirements, and also ensures the effectiveness of the traction.

[0030] 2. This invention analyzes the availability coefficient of each traction device based on the patient's fracture type, past medical history, and information on each traction device. Based on the availability coefficient of each traction device, it obtains each backup traction device, retrieves the cost of each backup traction device from the database, compares it with the range of costs that the patient can afford, and selects the final traction device, thus ensuring that the traction device meets the patient's usage needs.

[0031] 3. This invention obtains the installation area of ​​the traction device from the database based on the fracture location, fracture type and traction device of each patient in history, sets each installation point in the installation area, and selects each backup installation point according to the position of each force point of each patient's fracture. At the same time, the installation position of the traction device is determined according to the distribution of tendons around each backup installation point and the pressure distribution of the traction device at the bottom of each backup installation point, ensuring that the installation position of the traction device meets the installation requirements.

[0032] 4. This invention obtains alternative traction plans based on the patient's age, weight, fracture location, fracture type, and past medical history. The traction angle and traction force of each alternative traction plan are applied to a three-dimensional skeletal model, and vital signs and muscle data are monitored in real time. The patient's tolerance coefficient to the traction angle and traction force of each alternative traction plan is analyzed, and the patient's traction plan is determined, ensuring the effectiveness of traction. Attached Figure Description

[0033] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0034] Figure 1 This is a schematic diagram of the implementation steps of the method of the present invention.

[0035] Figure 2 This is a schematic diagram of the system structure connection of the present invention. Detailed Implementation

[0036] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0037] Please see Figure 1 As shown, the present invention provides an orthopedic traction assistance method based on artificial intelligence, including the following steps: Step 1, data acquisition: using medical imaging equipment to acquire images of the patient's fracture site and establish a three-dimensional skeletal model of the patient.

[0038] It should be noted that the process of establishing a patient's three-dimensional skeletal model is as follows: First, the image is input into medical image processing software. Then, noise is removed from the image, and grayscale is adjusted. Next, algorithms such as threshold segmentation, region growing, and level set are used to segment the bones from the surrounding soft tissue and background. Then, based on the segmented image data, a three-dimensional reconstruction algorithm is used to convert the two-dimensional image data into a three-dimensional triangular mesh model. Finally, the model is smoothed and denoised.

[0039] Step 2: Determine the traction device: Obtain the patient's fracture type, past medical history, and information on each traction device. Analyze the availability coefficient of each traction device, and select the traction device for the patient based on the availability coefficient and the cost of each traction device.

[0040] It should be noted that the patient's fracture type, past medical history, and information on each traction device are obtained from the database.

[0041] It should also be noted that traction devices include skin traction devices, bone traction devices, and sling traction devices, etc. The information of each traction device includes the set of applicable fracture types and the set of inapplicable diseases.

[0042] Different traction devices have different contraindications. For example, if a patient has eczema, psoriasis, or thrombophlebitis, then the patient is not suitable for using a skin traction device.

[0043] It should be explained that fracture types include fissure fractures, transverse fractures, comminuted fractures, and impacted fractures.

[0044] In a specific embodiment, the determination of the traction device involves the following steps: The patient's fracture type, past medical history, and information on each traction device are retrieved from the database. The availability coefficient of each traction device is analyzed. If the availability coefficient of a traction device is 1, it indicates that the traction device meets the patient's needs. If the availability coefficient of a traction device is 0, it indicates that the traction device does not meet the patient's needs. This method is used to determine whether each traction device meets the patient's needs. Traction devices that meet the patient's needs are identified and referred to as backup traction devices. The required cost of each backup traction device is retrieved from the database and compared with the patient's affordability. Backup traction devices whose costs are within the patient's affordability are identified and referred to as active traction devices. The required costs of each active traction device are compared, and the active traction device with the lowest required cost is selected as the traction device used by the patient.

[0045] The analysis of the availability coefficients of each traction device described above is specifically performed as follows: The patient's fracture type, past medical history, and information about each traction device are retrieved from the database and input into the fracture type model and past medical history model. The fracture type conformity value of each traction device is then output. Consistency value with past medical history ,but: In the formula This represents the preset coefficient threshold. Representing the Availability coefficient of each traction device Represents the number of each traction device. =1,2,3,..., , Represents the total number of traction devices. and All are positive integers.

[0046] It should be noted that, .

[0047] It should also be noted that the fracture type model is as follows: In the formula This represents the patient's fracture type. Representing the The set of fracture types to which each traction device is applicable. Each element in represents the first The various fracture types to which each traction device is applicable.

[0048] The above-mentioned past medical history model: In the formula Representing the patient's past medical history Each disease is represented by its corresponding disease number. =1,2,3,..., , Represents the total number of diseases. and All are positive integers. Representing the A traction device is not suitable for a collection of diseases. Each element in represents the first Each traction device is not suitable for any particular disease, among which This indicates that the patient has a disease in their past medical history in the first year of treatment. The traction device is not applicable to the set of diseases. This indicates that none of the diseases in the patient's past medical history are listed in the first category. The traction device is not applicable to the set of diseases.

[0049] Step 3: Determine the installation location of the traction device: Plan the installation area of ​​the traction device, and set each installation point in the installation area according to the preset first distance threshold. Obtain the location of each force point of the fracture site, analyze the influence index of each installation point on the patient's movement, and select each backup installation point. Based on the tendon distribution of each backup installation point and the bottom pressure distribution of the traction device at each backup installation point, analyze the installation coefficient of each backup installation point, compare them, and select the backup installation point with the highest installation coefficient as the installation location of the traction device.

[0050] It should be noted that the preset first distance threshold is the critical value for setting the distance between each installation point, which is set by medical staff based on the historical installation positions of the traction device.

[0051] It should also be noted that the points of force exertion differ depending on the body part. Taking the arm as an example, the points of force exertion in the arm include the biceps, triceps, and forearm muscles.

[0052] In a specific embodiment, the process of determining the installation location of the traction device is as follows: S11, obtain the patient's fracture location, fracture type, and traction device, and obtain the fracture location, fracture type, and traction device of each historical patient from the database. Compare the fracture location, fracture type, and traction device of each historical patient with the fracture location, fracture type, and traction device of the current patient. If the fracture location, fracture type, and traction device of a certain historical patient are all the same as those of the current patient, then obtain the installation location of the traction device of that historical patient and call this installation location the historical installation location. Obtain each historical installation location of the traction device in this way, and cluster each historical installation location to obtain the installation area of ​​the traction device.

[0053] S12. Within the installation area, each installation point is set according to a preset first distance threshold, and the positions of each force exertion point at the patient's fracture site are obtained. Based on the positions of each force exertion point and each installation point, the influence index of the installation point on the patient's movement is analyzed. If the influence index of a certain installation point on the patient's movement is 1, it means that the installation point affects the patient's movement. If the influence index of a certain installation point on the patient's movement is 0, it means that the installation point does not affect the patient's movement. This method is used to determine whether each installation point affects the patient's movement, and each installation point that does not affect the patient's movement is called a backup installation point.

[0054] It should be noted that in the 3D skeletal model, a 3D coordinate system is established with the center point of the 3D skeletal model as the origin. The force points of each movement at the fracture site are marked in the 3D skeletal model, and the coordinates of each force point in the 3D coordinate system are obtained.

[0055] It should also be noted that the point of force exertion during exercise bears a great deal of force and pressure. If the traction device is installed near the point of force exertion, it can increase local pressure and friction, which can easily lead to damage to muscles, tendons, ligaments and other tissues, and increase the risk of fractures.

[0056] S13. At the bottom of the traction device, set up each collection point according to the preset second distance threshold, install pressure sensors at each collection point, simulate the installation of each backup installation point on the patient's three-dimensional bone model, and collect the pressure of each collection point at the bottom of the traction device during the simulation installation process. At the same time, obtain the position of each tendon around each backup installation point, analyze the installation coefficient of each backup installation point, compare them, select the backup installation point with the highest installation coefficient, and use its position as the installation position of the traction device.

[0057] It should be noted that the preset second distance threshold is a critical value for setting the distance between each collection point, and it is set by the staff.

[0058] It should also be noted that the simulated installation process is as follows: the coordinates of each backup installation point in the three-dimensional bone model are obtained, a virtual traction device is generated, and pressure sensors are installed at each collection point at the bottom of the virtual traction device. When the doctor installs the virtual traction device on each backup installation point in the three-dimensional bone model, the pressure sensors installed at each collection point obtain the pressure at each collection point.

[0059] The above-mentioned analysis of the impact of the installation points on the patient's movement is carried out in the following specific process: The coordinates of each force exertion point in the patient's three-dimensional skeletal model and the coordinates of each installation point are obtained; the distance between each installation point and each force exertion point is calculated; and then, based on the analysis formula: Get the first Indicators of the impact of each installation point on patient movement In the formula Representing the The installation point and the first The distance between the points of force application This represents the preset third distance threshold. The number representing each installation point =1,2,3,..., , Represents the total number of installation points. Represents the total number of all points of force application. =1,2,3,..., , The total number of points of force application. , , and All are positive integers.

[0060] It should be noted that the principle of obtaining the coordinates of each installation point is the same as that of obtaining the coordinates of the point of force application.

[0061] It should also be noted that, , Representing the The coordinates of each installation point Representing the The coordinates of each point of force application.

[0062] In the above, This represents when the traction device is installed in the first When there are multiple installation points, there exists a point where the distance between the point of force application and the installation point is less than a preset third distance threshold. This represents when the traction device is installed in the first When there are multiple installation points, the distance between each point of force application and the installation point is greater than the preset third distance threshold.

[0063] The preset third distance threshold is a boundary value used to assess whether the distance between each installation point and each point of force exertion meets the requirements, and it is set by medical staff.

[0064] The above-mentioned analysis of the installation coefficient of each backup installation point is specifically carried out as follows: S21, obtain the pressure of each collection point at the bottom of the traction device at each backup installation point and the coordinates of each tendon around each backup installation point, and calculate the distance between each backup installation point and each tendon around it.

[0065] It should be noted that the principle of obtaining the coordinates of each tendon is the same as that of obtaining the coordinates of the point of force application during movement.

[0066] S22. Combine each sampling point at the bottom of the traction device in pairs to obtain each combination. Calculate the pressure difference between the two sampling points in each combination, and use this difference as the difference between the combinations. Then, normalize the result according to the analysis formula: Get the first Installation coefficient of backup installation points In the formula The traction device is represented in the first The first backup installation point The difference between the combinations, Representing the The backup installation point and its surrounding area The distance between the tendons, This represents the number of each backup installation point. =1,2,3,..., , This represents the total number of backup installation points. The number representing each combination, =1,2,3,..., , Represents the total number of combinations. The numbers representing the tendons, =1,2,3,..., , Represents the total number of tendons. , , , , and All are positive integers.

[0067] It should be noted that tendons bear significant tension and pressure during exercise. Attaching traction devices near tendons may increase the extra burden on tendons, causing abnormal traction or friction, thereby increasing the risk of injuries such as tendinitis and tendon tears.

[0068] It should also be noted that the balanced pressure at the bottom of the traction device ensures that the friction between the traction device and the patient's body is evenly distributed, which helps to maintain the stability of the traction device and reduces the risk of device displacement caused by uneven local pressure. At the same time, the balanced pressure can prevent problems such as pressure sores and blood circulation disorders caused by excessive pressure on the local skin and soft tissue.

[0069] in, In the formula Representing the Tendon coordinates Representing the The coordinates of the backup installation points are obtained from the 3D skeletal model, where the coordinates of each tendon are obtained from the model.

[0070] Step 4: Determine the traction plan: Obtain the patient's age, weight, fracture location, and past medical history, and retrieve all alternative traction plans from the database. Based on the traction force and traction angle of each alternative traction plan, determine the patient's final traction plan.

[0071] In a specific embodiment, the process of obtaining the final traction plan for the patient is as follows: S31, obtain the patient's age, weight, fracture location, fracture type, and past medical history, and compare them with the age, weight, fracture location, fracture type, and past medical history of historical patients. Analyze the return value of the physical status of historical patients and this patient. If the return value of the physical status of a historical patient is 1, it means that the physical status of the historical patient and this patient is similar. If the return value of the physical status of a historical patient and this patient is 0, it means that the physical status of the historical patient and this patient is different. Obtain the physical status return value of historical patients with a physical status return value of 1, and obtain their traction plans from the database. The traction plans of historical patients with a physical status return value of 1 are called each backup traction plan.

[0072] S32. Obtain the traction angle and traction force of each backup traction scheme and apply them to the patient's three-dimensional skeletal model. When simulating each backup scheme in the patient's three-dimensional skeletal model, monitor the vital signs and muscle data in real time, analyze the patient's tolerance coefficient to the traction angle and traction force of each backup traction scheme, calculate the difference between the patient's tolerance coefficient to the traction angle and traction force of each backup traction scheme and the optimal tolerance coefficient, compare them, and select the backup traction scheme with the smallest difference as the patient's final traction scheme.

[0073] It should be noted that the simulation process for each backup plan is as follows: When the doctor installs the virtual traction device on the 3D skeletal model, a physical model of the vascular system is established and connected to the 3D skeletal model. At the same time, sensors such as pressure sensors, optical sensors, and photoelectric pulse sensors are installed in the physical model of the vascular system, while sensors such as fiber optic grating sensors, surface electromyography sensors, and optical sensors are installed in the 3D skeletal model to obtain the traction angle and traction force of each backup traction plan. The doctor adjusts the virtual traction device according to the traction angle and traction force of each backup traction plan. After the adjustment is completed, within the preset traction time, the pressure sensors, photoelectric pulse sensors, fiber optic grating sensors, surface electromyography sensors, and optical sensors are used to collect blood pressure, pulse, muscle tension, muscle fatigue level, muscle circumference, and blood oxygen saturation in real time.

[0074] The process of establishing a physical model of the vascular system described above is as follows: First, medical imaging technology acquires image data of the patient's vascular system and collects physiological parameters related to the vascular system, such as blood pressure, heart rate, and blood viscosity. Second, the acquired medical image data is subjected to noise reduction, grayscale normalization, and threshold segmentation. Image processing algorithms are used to extract the contour information of the blood vessels. At the same time, a three-dimensional reconstruction algorithm is used to convert the two-dimensional contour information into a three-dimensional vascular model. Finally, fluid dynamics principles are introduced into the vascular model to simulate the flow of blood within the blood vessels.

[0075] It should also be noted that the vital signs data include blood pressure, blood oxygen saturation, and pulse.

[0076] The data for each muscle include muscle tension, muscle fatigue level, and muscle circumference.

[0077] It needs to be explained that by obtaining the patient's vital sign data and muscle data at various time points before fracture, calculating the average of the vital sign data and the average of the muscle data, and then normalizing them, the following can be achieved: In the formula Represents the optimal tolerance coefficient. Representing the The average value of each vital sign data Representing the The average of individual muscle data. Represents the coefficient of fluctuation in vital signs. Represents the muscle variability coefficient. Representing the Standard values ​​for individual life weight data Representing the Standard values ​​for muscle data.

[0078] The above-mentioned analysis of the historical patients and the patient's physical condition return values ​​is specifically performed as follows: The patient's fracture location, fracture type, and past medical history are retrieved from the database along with the fracture locations, fracture types, and past medical history of all historical patients. These are then input into the analysis model, which outputs the historical patients' and the patient's condition return values. The analysis is then performed according to the following formula: To obtain the historical number The patient and the patient's physical status return value. In the formula , These represent the patient's age and weight, respectively. , Representing the historical number The patient's age and weight, Representing history Each patient and the patient's condition return value , These represent the preset age difference threshold and the preset weight difference threshold, respectively. The numbers representing the patients in history, =1,2,3,..., , Represents the total number of historical patients. and All are positive integers.

[0079] It should be noted that the preset age difference threshold is a critical value used to analyze whether the patient's age is similar to the ages of previous patients, and it is set by medical staff.

[0080] It should also be noted that the preset weight difference threshold is a critical value used to analyze whether the patient's weight is similar to the weight of other patients in the past, and it is set by medical staff.

[0081] It needs to be explained that the analytical model is as follows: In the formula , , These represent the patient's fracture location, fracture type, and medical history, respectively. , , Representing the historical number The location, type, and medical history of each patient's fracture.

[0082] The above-mentioned analysis of the patient's tolerance coefficient to the traction angle and traction force in each alternative traction plan involves the following steps: Vital sign data and muscle data at each traction moment are obtained when simulating each alternative traction plan in a three-dimensional skeletal model. These are then normalized and input into the vital sign data fluctuation model and the muscle data fluctuation model. The output is the vital sign fluctuation coefficient and muscle fluctuation coefficient when simulating each alternative plan in the three-dimensional skeletal model. Simultaneously, the average value of each vital sign data and the average value of each muscle data are calculated. Then, based on the analysis formula: Obtain the patient's opinion on the first The tolerance coefficients of traction angle and traction force in the backup traction scheme In the formula This represents simulating the first in a 3D skeletal model. The backup plan is the first The average value of each vital sign data This represents simulating the first in a 3D skeletal model. The backup plan is the first The average of individual muscle data. Representing the Standard values ​​for each vital sign data point Representing the Standard values ​​for muscle data, This represents simulating the first in a 3D skeletal model. The coefficient of vital sign fluctuation in the backup plan. This represents simulating the first in a 3D skeletal model. Muscle variability coefficient in backup plans The numbers representing the backup plans, =1,2,3,..., , Represents the total number of backup plans. The numbers representing the various vital signs data. =1,2,3,..., , The total number of vital signs data. The number representing the data for each muscle. =1,2,3,..., , The total number of muscle data. , , , , and All are positive integers.

[0083] It should be noted that the expression for the vital signs data fluctuation model is as follows: In the formula This represents simulating the first in a 3D skeletal model. The backup plan is the first The vital signs data were in the first The values ​​at each simulated time point, This represents simulating the first in a 3D skeletal model. The backup plan is the first The vital signs data were in the first The values ​​at each simulated time point, The numbers representing each simulation time point, =1,2,3,..., , Represents the total number of simulation moments. and All are positive integers.

[0084] It should also be noted that the expression for the muscle data fluctuation model is: In the formula This represents simulating the first in a 3D skeletal model. The backup plan is the first The muscle data in the first The values ​​at each simulated time point, This represents simulating the first in a 3D skeletal model. The backup plan is the first The muscle data in the first The values ​​at each simulated time point.

[0085] The standard values ​​for each vital sign are threshold values ​​used to assess whether a patient's vital sign data are normal, and are set by medical staff.

[0086] It should be explained that the standard values ​​for each muscle data point are threshold values ​​used to assess whether a patient's muscle data points meet the requirements for normal exercise, and are set by medical staff.

[0087] Please see Figure 2 As shown, the present invention provides an orthopedic traction assistance system based on artificial intelligence, including the following modules: a data acquisition module for acquiring images of the patient's fracture site using medical imaging equipment and establishing a three-dimensional skeletal model of the patient.

[0088] The traction device determination module is used to obtain the patient's fracture type, past medical history, characteristics of each traction device, analyze the availability coefficient of each traction device, and select the traction device for the patient based on the availability of each traction device and the cost required for each traction device.

[0089] The traction device installation location determination module is used to plan the installation area of ​​the traction device and set each installation point in the installation area according to a preset first distance threshold. When the patient has no fracture, the force points of each movement at the fracture site are obtained. The influence index of each installation point on the patient's movement is analyzed, and each backup installation point is selected. Based on the tendon distribution of each backup installation point and the pressure distribution of the traction device at the bottom of each backup installation point, the installation coefficient of each backup installation point is analyzed and compared. The backup installation point with the highest installation coefficient is selected and its location is used as the installation position of the traction device.

[0090] The traction plan determination module is used to obtain the patient's age, weight, fracture location, and past medical history, and to retrieve various backup traction plans from the database. Based on the traction force and traction angle of each backup traction plan, the final traction plan for the patient is obtained.

[0091] The database is used to store historical information about each patient, information about each traction device, the patient's fracture type, age, fracture location, and weight.

[0092] It should be noted that the information for each patient in the history includes their age, weight, fracture location, fracture type, traction device, and the location where the traction device was installed.

[0093] This invention first acquires an image of the patient's fracture site and establishes a three-dimensional bone model. Then, based on the patient's fracture type, medical history, and the characteristics of each traction device, the traction device to be used is selected. Next, based on the force application points at the patient's fracture site, tendon distribution, and pressure distribution at the bottom of the traction device, the installation position of the traction device is determined. Finally, based on the patient's age, weight, fracture location, and medical history, alternative traction schemes are selected. The patient's tolerance coefficients to the traction angles and traction forces in each alternative traction scheme are analyzed. Based on the analysis results, the final traction scheme for the patient is determined, ensuring that the traction device meets the patient's usage needs, the installation position meets installation requirements, and the accuracy of installation and the effectiveness of traction are also guaranteed.

[0094] The above description is merely an example and illustration of the concept of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described or use similar methods to replace them, as long as they do not deviate from the concept of the invention or exceed the scope defined in this specification, they should all fall within the protection scope of the present invention.

Claims

1. An orthopedic traction-assisted method based on artificial intelligence, characterized in that, Includes the following steps: Step 1: Data Acquisition: Use medical imaging equipment to acquire images of the patient's fracture site and create a three-dimensional skeletal model of the patient; Step 2: Determine the traction device: Obtain the patient's fracture type, past medical history, and information on each traction device; analyze the availability coefficient of each traction device; and select the traction device for the patient based on the availability coefficient and the cost of each traction device. Step 3: Determine the installation location of the traction device: Plan the installation area of ​​the traction device, and set each installation point in the installation area according to the preset first distance threshold. Obtain the location of each force point of the fracture site, analyze the influence index of each installation point on the patient's movement, and select each backup installation point. Based on the tendon distribution of each backup installation point and the bottom pressure distribution of the traction device at each backup installation point, analyze the installation coefficient of each backup installation point, compare them, and select the backup installation point with the highest installation coefficient as the installation location of the traction device. Step 4: Determine the traction plan: Obtain the patient's age, weight, fracture location, and past medical history, and retrieve all alternative traction plans from the database. Based on the traction force and traction angle of each alternative traction plan, determine the patient's final traction plan.

2. The orthopedic traction assistance method based on artificial intelligence according to claim 1, characterized in that, The specific process for determining the traction device is as follows: The system retrieves the patient's fracture type, medical history, and information on each traction device from the database. It then analyzes the availability coefficient of each traction device. If the availability coefficient of a traction device is 1, it indicates that the device meets the patient's needs; if the availability coefficient is 0, it indicates that the device does not meet the patient's needs. This method is used to determine whether each traction device meets the patient's needs, and the traction devices that meet the patient's needs are identified as backup traction devices. The required cost of each backup traction device is retrieved from the database and compared with the patient's affordable budget. Backup traction devices whose costs fall within the patient's budget are identified as the active traction devices. Finally, the costs of each active traction device are compared, and the active traction device with the lowest cost is selected as the traction device used by the patient.

3. The orthopedic traction assistance method based on artificial intelligence according to claim 2, characterized in that, The specific process for analyzing the availability coefficient of each traction device is as follows: The system retrieves the patient's fracture type, medical history, and information on each traction device from the database, and inputs this information into the fracture type model and the medical history model. The system then outputs the fracture type conformity value for each traction device. Consistency value with past medical history ,but: ； In the formula This represents the preset coefficient threshold. Representing the Availability coefficient of each traction device Represents the number of each traction device. =1,2,3,..., , Represents the total number of traction devices. and All are positive integers.

4. The orthopedic traction assistance method based on artificial intelligence according to claim 1, characterized in that, The specific process for determining the installation location of the traction device is as follows: S11. Obtain the patient's fracture location, fracture type, and traction device. Also, obtain the fracture location, fracture type, and traction device of each historical patient from the database. Compare the fracture location, fracture type, and traction device of each historical patient with the fracture location, fracture type, and traction device of the current patient. If the fracture location, fracture type, and traction device of a certain historical patient are all the same as those of the current patient, then obtain the installation location of the traction device of that historical patient and call this installation location the historical installation location. Obtain each historical installation location of the traction device in this way, and cluster each historical installation location to obtain the installation area of ​​the traction device. S12. Within the installation area, each installation point is set according to a preset first distance threshold, and the positions of each force exertion point at the patient's fracture site are obtained. Based on the positions of each force exertion point and each installation point, the influence index of the installation point on the patient's movement is analyzed. If the influence index of a certain installation point on the patient's movement is 1, it means that the installation point affects the patient's movement. If the influence index of a certain installation point on the patient's movement is 0, it means that the installation point does not affect the patient's movement. This method is used to determine whether each installation point affects the patient's movement, and each installation point that does not affect the patient's movement is called a backup installation point. S13. At the bottom of the traction device, set up each collection point according to the preset second distance threshold, install pressure sensors at each collection point, simulate the installation of each backup installation point on the patient's three-dimensional bone model, and collect the pressure of each collection point at the bottom of the traction device during the simulation installation process. At the same time, obtain the position of each tendon around each backup installation point, analyze the installation coefficient of each backup installation point, compare them, select the backup installation point with the highest installation coefficient, and use its position as the installation position of the traction device.

5. The orthopedic traction assistance method based on artificial intelligence according to claim 4, characterized in that, The specific process for analyzing the impact of the installation point on the patient's movement is as follows: Obtain the coordinates of each force exertion point in the patient's 3D skeletal model and the coordinates of each mounting point, calculate the distance between each mounting point and each force exertion point, and then apply the analysis formula: Get the first Indicators of the impact of each installation point on patient movement In the formula Representing the The installation point and its surroundings The distance between the points of force application This represents the preset third distance threshold. The number representing each installation point =1,2,3,..., , Represents the total number of installation points. Represents the total number of all points of force application. =1,2,3,..., , The total number of points of force application. , , and All are positive integers.

6. The orthopedic traction assistance method based on artificial intelligence according to claim 4, characterized in that, The specific process for analyzing the installation coefficients of each backup installation point is as follows: S21. Obtain the pressure of each collection point at the bottom of the traction device at each backup installation point and the coordinates of each tendon around each backup installation point, and calculate the distance between each backup installation point and each tendon around it. S22. Combine each sampling point at the bottom of the traction device in pairs to obtain each combination. Calculate the pressure difference between the two sampling points in each combination, and use this difference as the difference between the combinations. Then, normalize the result according to the analysis formula: Get the first Installation coefficient of backup installation points In the formula The traction device is represented in the first The first backup installation point The difference between the combinations, Representing the The backup installation point and its surrounding area The distance between the tendons, This represents the number of each backup installation point. =1,2,3,..., , This represents the total number of backup installation points. The number representing each combination, =1,2,3,..., , Represents the total number of combinations. The numbers representing the tendons, =1,2,3,..., , Represents the total number of tendons. , , , , and All are positive integers.

7. The orthopedic traction assistance method based on artificial intelligence according to claim 1, characterized in that, The specific process for obtaining the patient's final traction plan is as follows: S31. Obtain the patient's age, weight, fracture location, fracture type, and past medical history, and compare them with the age, weight, fracture location, fracture type, and past medical history of historical patients. Analyze the physical status return values ​​of historical patients and this patient. If the physical status return value of a historical patient is 1, it means that the physical status of the historical patient and this patient is similar. If the physical status return value of a historical patient and this patient is 0, it means that the physical status of the historical patient and this patient is different. Obtain the physical status return values ​​of historical patients with 1, and obtain their traction plans from the database. The traction plans of historical patients with 1 physical status return values ​​are called backup traction plans. S32. Obtain the traction angle and traction force of each backup traction scheme and apply them to the patient's three-dimensional skeletal model. When simulating each backup scheme in the patient's three-dimensional skeletal model, monitor the vital signs and muscle data in real time, analyze the patient's tolerance coefficient to the traction angle and traction force of each backup traction scheme, calculate the difference between the patient's tolerance coefficient to the traction angle and traction force of each backup traction scheme and the optimal tolerance coefficient, compare them, and select the backup traction scheme with the smallest difference as the patient's final traction scheme.

8. The orthopedic traction assistance method based on artificial intelligence according to claim 7, characterized in that, The analysis of historical data for each patient and the patient's physical status return values ​​is performed as follows: The model inputs the patient's fracture location, fracture type, and past medical history into the database, along with the fracture location, fracture type, and past medical history of historical patients. It then outputs the condition return values ​​of historical patients and the current patient, based on the analysis formula: To obtain the historical number The patient and the patient's physical status return value. In the formula , These represent the patient's age and weight, respectively. , Representing the historical number The patient's age and weight, Representing history Each patient and the patient's condition return value , These represent the preset age difference threshold and the preset weight difference threshold, respectively. The numbers representing the patients in history, =1,2,3,..., , Represents the total number of historical patients. and All are positive integers.

9. The orthopedic traction assistance method based on artificial intelligence according to claim 7, characterized in that, The analysis of patients' tolerance coefficients to the traction angle and traction force of each alternative traction regimen is carried out in the following manner: Acquire vital sign data and muscle data at each traction moment when simulating various alternative traction schemes in a 3D skeletal model, and input them into the vital sign data fluctuation model and muscle data fluctuation model. Output the vital sign fluctuation coefficient and muscle fluctuation coefficient when simulating each alternative scheme in the 3D skeletal model. Simultaneously calculate the average value of each vital sign data and the average value of each muscle data, and perform normalization processing according to the analysis formula: Obtain the patient's opinion on the first The tolerance coefficients of traction angle and traction force in the backup traction scheme In the formula This represents simulating the first in a 3D skeletal model. The backup plan is the first The average value of each vital sign data This represents simulating the first in a 3D skeletal model. The backup plan is the first The average of individual muscle data. Representing the Standard values ​​for each vital sign data point Representing the Standard values ​​for muscle data, This represents simulating the first in a 3D skeletal model. The coefficient of vital sign fluctuation in the backup plan. This represents simulating the first in a 3D skeletal model. Muscle variability coefficient in backup plans The numbers representing the backup plans, =1,2,3,..., , Represents the total number of backup plans. The numbers representing the various vital signs data. =1,2,3,..., , The total number of vital signs data. The number representing the data for each muscle. =1,2,3,..., , The total number of muscle data. , , , , and All are positive integers.

10. An orthopedic traction assist system for implementing the orthopedic traction assist method based on artificial intelligence as described in any one of claims 1-9, characterized in that, include: The data acquisition module is used to acquire images of the patient's fracture site using medical imaging equipment and to build a three-dimensional skeletal model of the patient; The traction device determination module is used to obtain the patient's fracture type, past medical history, and information on each traction device, analyze the availability coefficient of each traction device, and select the traction device for the patient based on the availability of each traction device and the cost of each traction device. The traction device installation location determination module is used to plan the installation area of ​​the traction device, and set each installation point in the installation area according to the preset first distance threshold. It obtains the position of each force point of movement at the fracture site, analyzes the influence index of each installation point on the patient's movement, and selects each backup installation point. Based on the tendon distribution of each backup installation point and the bottom pressure distribution of the traction device at each backup installation point, it analyzes the installation coefficient of each backup installation point, compares them, and selects the backup installation point with the highest installation coefficient as the installation position of the traction device. The traction plan determination module is used to obtain the patient's age, weight, fracture location and past medical history, and to obtain each alternative traction plan from the database. Based on the traction force and traction angle in each alternative traction plan, the final traction plan for the patient is obtained. The database is used to store historical information about each patient, information about each traction device, the patient's fracture type, age, fracture location, and weight.

Images