Cold ground full orthopedics intelligent diagnosis and treatment system

Abstract

The application provides a cold region all-orthopedics intelligent diagnosis and treatment system, comprising: an intelligent auxiliary evaluation module for cold region all-orthopedics disease auxiliary evaluation according to patient treatment data and cold region specificity data; an intelligent operation planning module for hip and knee joint preoperative planning, spine preoperative planning, sports medicine preoperative planning, and trauma operation planning according to patient treatment data and cold region specificity data; an intelligent robot module for equipment control and voice interaction according to intraoperative interaction requirements; intraoperative real-time prompt according to the preoperative operation plan, real-time generation of operation suggestion, real-time update of the control mode of the operation robot; a remote module for remote operation, remote multidisciplinary consultation, intraoperative medical data calling, and pre-hospital emergency remote cooperation; and a postoperative rehabilitation module for postoperative evaluation and generation of a personalized rehabilitation plan of a patient according to postoperative data and the preoperative planning plan.

Description

Technical Field

[0001] This application belongs to the field of digital orthopedic diagnosis and treatment, and in particular relates to a digital orthopedic diagnosis and treatment system for cold regions. Background Technology

[0002] The ice and snow economy, centered on ice and snow resources, encompasses a comprehensive industry including ice and snow tourism, ice and snow sports, ice and snow equipment manufacturing, and ice and snow culture, and has become an important new driving force for China's economic growth. However, with the rapid development of the ice and snow economy, various chronic and acute orthopedic diseases, such as fractures and sports injuries, are also on the rise.

[0003] Currently, orthopedic diagnosis and treatment is mainly general, lacking specific solutions designed for orthopedic conditions in cold regions, making it difficult to meet the personalized treatment needs of doctors and patients in cold regions. Summary of the Invention

[0004] This application provides a digital intelligent diagnosis and treatment system for orthopedics in cold regions, which can realize intelligent auxiliary assessment, intelligent surgical planning, intelligent robot control, remote control, and postoperative rehabilitation functions, and can meet the personalized diagnosis and treatment needs of doctors and patients in cold regions.

[0005] In a first aspect, embodiments of this application provide a digital intelligent diagnosis and treatment system for all orthopedics in cold regions, including: The intelligent auxiliary assessment module is used to conduct auxiliary assessment of all orthopedic diseases in cold regions based on patient visit data and cold-region-specific data. The intelligent surgical planning module is used to perform preoperative planning for hip and knee joint surgery, spinal surgery, sports medicine surgery, and trauma surgery based on patient medical data and cold-region-specific data. The intelligent robot module is used to respond to intraoperative interaction needs, control the equipment and perform voice interaction based on these needs; provide real-time intraoperative prompts based on the preoperative surgical plan; generate surgical operation suggestions in real time during the operation and update the surgical plan in real time based on the response results of the surgical operation suggestions to obtain the updated real-time surgical plan; control the surgical robot to assist in performing surgical operations based on the preoperative surgical plan and intraoperative perception data; and update the control mode of the surgical robot in real time. The remote module is used to perform preliminary assessments based on received remote medical data from users and to feed the preliminary assessment results back to the user's terminal; to perform rehabilitation assessments based on received remote rehabilitation data from patients, and to update the patient's rehabilitation plan in real time based on the rehabilitation assessment results and cold environment data; to conduct live surgical demonstrations and automatically generate surgical teaching videos based on the live broadcast content; to control the surgical robot according to received remote surgical instructions to realize remote surgery; and to conduct remote multidisciplinary consultations, intraoperative medical data retrieval, and remote pre-hospital emergency care collaboration. The postoperative rehabilitation module is used to conduct postoperative assessments based on patient postoperative data and preoperative planning, obtaining postoperative assessment results. Based on the postoperative assessment results, patient attribute information, and medical records, it generates personalized rehabilitation plans for the patient. These personalized rehabilitation plans include in-hospital and out-of-hospital rehabilitation plans, with the out-of-hospital plan including cold-climate-specific rehabilitation suggestions. The module simulates joint mobility and pain indicators under cold-climate conditions based on the patient's in-hospital rehabilitation assessment data to assess whether the patient meets the discharge criteria for cold-climate environments. Finally, it conducts rehabilitation assessments based on the patient's out-of-hospital rehabilitation assessment data, obtaining rehabilitation assessment results, and updates the out-of-hospital rehabilitation plan accordingly.

[0006] Optionally, the intelligent assisted evaluation module is specifically used for: Patient medical data and cold-region sports injury-specific data are input into a pre-trained intelligent sports injury analysis model to obtain an intelligent sports injury analysis report output by the model. The sports injury intelligent analysis report includes the injury type, injury severity, risk assessment results, assessment recommendations, rehabilitation recommendations, and cold-weather-specific recommendations.

[0007] Optionally, the intelligent assisted evaluation module is specifically used for: Patient medical data and cold-region-specific osteoporosis data are input into a pre-trained osteoporosis assessment model to obtain an osteoporosis auxiliary assessment report output by the osteoporosis assessment model. The osteoporosis auxiliary assessment report includes osteoporosis risk level, osteoporosis type prediction, fracture risk prediction, and personalized intervention recommendations.

[0008] Optionally, the intelligent surgical planning module is specifically used for: A three-dimensional model of the knee joint is obtained by performing three-dimensional reconstruction based on the acquired medical images of the knee joint. Preoperative planning is performed based on a three-dimensional model of the knee joint to obtain an initial preoperative planning scheme for knee replacement. Based on bone data associated with total knee arthroplasty, the initial preoperative planning scheme for knee arthroplasty was optimized to obtain the optimized preoperative planning scheme. After performing a simulated surgery based on the optimized preoperative planning scheme, postoperative motion simulation of the knee joint was conducted to determine whether various knee joint motion simulations could achieve the corresponding normal joint range of motion. If at least one knee joint motion simulation fails to achieve the corresponding normal joint range of motion, the optimized preoperative planning scheme will be adjusted until a target preoperative planning scheme that meets the motion simulation requirements is obtained.

[0009] Optionally, the intelligent surgical planning module is specifically used for: A three-dimensional model of the hip joint is obtained by performing three-dimensional reconstruction based on the acquired medical images of the hip joint. Based on the three-dimensional model of the hip joint, an initial preoperative planning scheme for periacetabular osteotomy was obtained. Based on bone data associated with periacetabular osteotomy, the initial preoperative planning scheme for knee replacement was optimized to obtain the optimized preoperative planning scheme. After performing a simulated surgery based on the optimized preoperative planning scheme, postoperative motion simulation of the hip joint was conducted to determine whether various motion simulations could achieve the corresponding normal joint range of motion. If at least one of the motion simulations fails to achieve the corresponding normal joint range of motion, the optimized preoperative planning scheme will be adjusted until a target preoperative planning scheme that satisfies the motion simulation requirements is obtained.

[0010] Optionally, the intelligent robot module is specifically used for: Based on intraoperative perception data, preoperative surgical plans, and pre-trained surgical robot decision-making and execution models, surgical robot operation decisions and control commands are generated in real time; among them, The surgical robot decision and execution model includes a surgical decision branch and a robot execution branch. The surgical decision branch is used to generate surgical robot operation decisions in real time based on intraoperative perception data and preoperative surgical plans. The robot execution branch is used to generate surgical robot control commands based on the surgical robot operation decisions.

[0011] Optionally, the intelligent robot module is specifically used for: Based on the control modes corresponding to each surgical stage planned in the preoperative plan and the intraoperative sensing data, the surgical robot is controlled to assist in performing surgical operations according to the corresponding control modes. The control modes of surgical robots include local control, remote control, and autonomous control.

[0012] Optionally, the remote module is specifically used for: A rehabilitation assessment is conducted based on the received remote rehabilitation data from the patient to determine the patient's current rehabilitation progress; wherein, the remote rehabilitation data from the patient includes exercise verification videos, medical imaging data, medical test data, and rehabilitation progress description information; Based on the deviation between the patient's current recovery progress and the estimated recovery progress, the patient's recovery plan is updated in real time in conjunction with data on the cold environment.

[0013] Optionally, the postoperative rehabilitation module is specifically used for: Based on postoperative assessment results, patient attribute information, and medical records, an in-hospital rehabilitation plan tailored to the patient is generated; among which, The in-hospital rehabilitation program includes in-hospital nursing care, physical therapy, nutrition, exercise, and discharge criteria.

[0014] Optionally, the postoperative rehabilitation module is specifically used for: Based on the patient's in-hospital rehabilitation assessment data, simulate the patient's joint activity index and pain index under cold environment conditions, and assess whether the patient meets the discharge criteria under cold environment conditions based on the simulation results; If the patient meets the matching discharge criteria, a home rehabilitation assessment is conducted based on the patient's home temperature data and in-hospital rehabilitation assessment data to determine whether the patient meets the conditions for home rehabilitation.

[0015] Secondly, embodiments of this application provide a control method for a digital intelligent diagnosis and treatment system for all-round orthopedics in cold regions. The intelligent method is used to realize the functions of the digital intelligent diagnosis and treatment system for all-round orthopedics in cold regions as described in any embodiment of the first aspect.

[0016] Thirdly, embodiments of this application provide an electronic device, which includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it realizes the functions of the cold-region orthopedic digital intelligent diagnosis and treatment system.

[0017] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer program instructions, which, when executed by a processor, implement the functions of a digital and intelligent diagnosis and treatment system for orthopedics in cold regions.

[0018] The cold-region comprehensive orthopedic digital diagnosis and treatment system, control method, equipment and computer-readable storage medium of this application embodiment provide intelligent auxiliary assessment module, intelligent surgical planning module, intelligent robot module, remote module and postoperative rehabilitation module, which can realize intelligent auxiliary assessment, intelligent surgical planning, intelligent robot control, remote control and diagnosis and treatment, and postoperative rehabilitation functions, and can meet the personalized diagnosis and treatment needs of medical staff and patients in cold regions. Attached Figure Description

[0019] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0020] Figure 1 This is a schematic diagram of the architecture of a digital intelligent diagnosis and treatment system for all orthopedics in cold regions provided in one embodiment of this application; Figure 2 This is a schematic diagram showing the architectural details of a digital and intelligent diagnosis and treatment system for all orthopedics in cold regions, provided in one embodiment of this application. Figure 3 This is a schematic diagram of the architecture of the intelligent auxiliary assessment model in the cold-region orthopedic digital diagnosis and treatment system provided in one embodiment of this application; Figure 4 This is a schematic diagram of the architecture of the cold-region population skeletal digital model library in the cold-region comprehensive orthopedic digital diagnosis and treatment system provided in one embodiment of this application; Figure 5 This is a schematic diagram of the interface of the operating software in the digital diagnosis and treatment system for all orthopedics in cold regions provided in one embodiment of this application; Figure 6 This is a schematic diagram of the architecture of the surgical robot decision-making and execution model in the digital intelligent diagnosis and treatment system for all orthopedics in cold regions provided in one embodiment of this application; Figure 7 This is a schematic diagram of the intelligent control decision-making architecture in a digital and intelligent diagnosis and treatment system for all orthopedics in cold regions provided in one embodiment of this application; Figure 8 This is a schematic diagram of the architecture of the remote module in the cold-region orthopedic digital diagnosis and treatment system provided in one embodiment of this application; Figure 9 This is a schematic diagram of the architecture of remote diagnosis and treatment in a cold-region orthopedic digital diagnosis and treatment system provided in one embodiment of this application, which incorporates a digital bone model library of cold-region populations. Figure 10 This is a schematic diagram of the architecture of the cold-region orthopedic digital diagnosis and treatment system provided in one embodiment of this application, which manages the entire postoperative rehabilitation process based on a digital bone model library of cold-region populations. Figure 11 This is a schematic diagram of the structure of an electronic device provided in one embodiment of this application. Detailed Implementation

[0021] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0022] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0023] To address the problems of existing technologies, this application provides a digital intelligent diagnosis and treatment system for all-around orthopedics in cold regions. The following is a description of the digital intelligent diagnosis and treatment system for all-around orthopedics in cold regions provided by this application. Figure 1 This is a schematic diagram of the architecture of a digital intelligent diagnosis and treatment system for all-round orthopedics in cold regions provided in one embodiment of this application. The digital intelligent diagnosis and treatment system for all-round orthopedics in cold regions includes an intelligent auxiliary assessment module, an intelligent surgical planning module, an intelligent robot module, a remote module, and a postoperative rehabilitation module; wherein, The intelligent auxiliary assessment module is used to conduct auxiliary assessment of all orthopedic diseases in cold regions based on patient visit data and cold-region-specific data. The intelligent surgical planning module is used to perform preoperative planning for hip and knee joint surgery, spinal surgery, sports medicine surgery, and trauma surgery based on patient medical data and cold-region-specific data. The intelligent robot module is used to respond to intraoperative interaction needs, control the equipment and perform voice interaction based on these needs; provide real-time intraoperative prompts based on the preoperative surgical plan; generate surgical operation suggestions in real time during the operation and update the surgical plan in real time based on the response results of the surgical operation suggestions to obtain the updated real-time surgical plan; control the surgical robot to assist in performing surgical operations based on the preoperative surgical plan and intraoperative perception data; and update the control mode of the surgical robot in real time. The remote module is used to perform preliminary assessments based on received remote medical data from users and to feed the preliminary assessment results back to the user's terminal; to perform rehabilitation assessments based on received remote rehabilitation data from patients, and to update the patient's rehabilitation plan in real time based on the rehabilitation assessment results and cold environment data; to conduct live surgical demonstrations and automatically generate surgical teaching videos based on the live broadcast content; to control the surgical robot according to received remote surgical instructions to realize remote surgery; and to conduct remote multidisciplinary consultations, intraoperative medical data retrieval, and remote pre-hospital emergency care collaboration. The postoperative rehabilitation module is used to conduct postoperative assessments based on patient postoperative data and preoperative planning, obtaining postoperative assessment results. Based on the postoperative assessment results, patient attribute information, and medical records, it generates personalized rehabilitation plans for the patient. These personalized rehabilitation plans include in-hospital and out-of-hospital rehabilitation plans, with the out-of-hospital plan including cold-climate-specific rehabilitation suggestions. The module simulates joint mobility and pain indicators under cold-climate conditions based on the patient's in-hospital rehabilitation assessment data to assess whether the patient meets the discharge criteria for cold-climate environments. Finally, it conducts rehabilitation assessments based on the patient's out-of-hospital rehabilitation assessment data, obtaining rehabilitation assessment results, and updates the out-of-hospital rehabilitation plan accordingly.

[0024] Figure 2 This is a schematic diagram showing the architectural details of a digital intelligent diagnosis and treatment system for all orthopedics in cold regions provided in one embodiment of this application.

[0025] For intelligent auxiliary assessment module, Figure 3 This is a schematic diagram of the architecture of the intelligent auxiliary assessment model in the cold-region orthopedic digital diagnosis and treatment system provided in one embodiment of this application.

[0026] In some embodiments, the intelligent assisted evaluation module is specifically used for: Patient medical data and cold-region sports injury-specific data are input into a pre-trained intelligent sports injury analysis model to obtain an intelligent sports injury analysis report output by the model. The sports injury intelligent analysis report includes the injury type, injury severity, risk assessment results, assessment recommendations, rehabilitation recommendations, and cold-weather-specific recommendations.

[0027] The intelligent sports injury analysis model includes a multi-dimensional feature extraction module, a cross-modal feature alignment module, a content recommendation engine based on a digital model library of bones of people in cold regions, and a sports injury analysis engine.

[0028] Figure 4 This is a schematic diagram of the architecture of the cold-region population skeletal digital model library in the cold-region comprehensive orthopedic digital diagnosis and treatment system provided in one embodiment of this application.

[0029] In some embodiments, the multidimensional feature extraction module may include a text feature extraction layer and an image feature extraction layer; the text feature extraction layer is configured as a BERT-based fine-tuned model, capable of extracting text features from input medical records and other related texts; the image feature extraction layer is configured as a ResNet-50 pre-trained model, capable of extracting features from input medical images and other images; the cross-modal feature alignment module includes a multimodal alignment network and an adaptive feature mapping layer; the multimodal alignment network uses contrastive learning and includes multiple projection heads (for patient consultation data and cold-region sports injury-specific data, respectively); the adaptive feature mapping layer is based on Transformer-based adaptive mapping, which can dynamically adjust the weights of different modal features, and the contrastive learning loss uses the InfoNCE loss function; the content recommendation engine and sports injury analysis engine based on the cold-region population skeletal digital model library can output corresponding content based on a graph neural network; the graph neural network can use a graph attention network (GAT) to process the cold-region population skeletal digital model library for sports injury analysis (injury type, injury degree, risk assessment results) and content recommendation (assessment suggestions, rehabilitation suggestions, cold-region-specific suggestions).

[0030] In some embodiments, the intelligent assisted evaluation module is specifically used for: Patient medical data and cold-region-specific osteoporosis data are input into a pre-trained osteoporosis assessment model to obtain an osteoporosis auxiliary assessment report output by the osteoporosis assessment model. The osteoporosis auxiliary assessment report includes osteoporosis risk level, osteoporosis type prediction, fracture risk prediction, and personalized intervention suggestions for cold regions.

[0031] The osteoporosis assessment model includes a multi-dimensional feature extraction module, a cross-modal feature alignment module, a content recommendation engine based on a digital model library of bones from cold-region populations, and an osteoporosis assessment engine.

[0032] In some embodiments, the multidimensional feature extraction module may include a text feature extraction layer and an image feature extraction layer; the text feature extraction layer is configured as a BERT-based fine-tuned model, capable of extracting text features from input case data and other relevant texts; the image feature extraction layer is configured as a ResNet-50 pre-trained model, capable of extracting features from input medical images and other images; the cross-modal feature alignment module includes a multimodal alignment network and an adaptive feature mapping layer; the multimodal alignment network uses contrastive learning and includes multiple projection heads (for patient consultation data and cold-region osteoporosis-specific data, respectively); the adaptive feature mapping layer is based on Transformer-based adaptive mapping, which can dynamically adjust the weights of different modal features, and the contrastive learning loss uses the InfoNCE loss function; the content recommendation engine and osteoporosis assessment engine based on the cold-region population skeletal digital model library can output corresponding content based on a graph neural network; the graph neural network can use a graph attention network (GAT) to process the cold-region population skeletal digital model library for osteoporosis assessment (osteoporosis risk level, osteoporosis type prediction, fracture risk prediction) and content recommendation (personalized intervention suggestions for cold regions).

[0033] In some embodiments, the intelligent assisted evaluation module is specifically used for: Patient medical data and cold-region-specific osteoarthritis data are input into a pre-trained intelligent osteoarthritis analysis model to obtain an intelligent osteoarthritis analysis report output by the model. The intelligent analysis report on osteoarthritis includes osteoarthritis auxiliary assessment results, degree of joint degeneration, progression risk assessment, cold environment impact assessment, and personalized intervention suggestions for cold regions.

[0034] The intelligent analysis model for osteoarthritis includes a multi-dimensional feature extraction module, a cross-modal feature alignment module, a content recommendation engine based on a digital model library of bones from cold-region populations, and an intelligent analysis engine for osteoarthritis.

[0035] In some embodiments, the multidimensional feature extraction module may include a text feature extraction layer and an image feature extraction layer; the text feature extraction layer is configured as a BERT-based fine-tuned model, capable of extracting text features from input case data and other relevant texts; the image feature extraction layer is configured as a ResNet-50 pre-trained model, capable of extracting features from input medical images and other images; the cross-modal feature alignment module includes a multimodal alignment network and an adaptive feature mapping layer; the multimodal alignment network uses contrastive learning and includes multiple projection heads (for patient consultation data and cold-region osteoarthritis-specific data, respectively); the adaptive feature mapping layer is based on Transformer-based adaptive mapping, which can dynamically adjust the weights of different modal features, and the contrastive learning loss uses the InfoNCE loss function; the content recommendation engine and osteoarthritis intelligent analysis engine based on the cold-region population skeletal digital model library can output corresponding content based on a graph neural network; the graph neural network can use a graph attention network (GAT) to process the cold-region population skeletal digital model library for intelligent analysis of osteoarthritis (osteoarthritis auxiliary assessment results, joint degeneration degree, progression risk assessment, cold-region environmental impact assessment) and content recommendation (cold-region personalized intervention suggestions).

[0036] In some embodiments, the intelligent assisted evaluation module is specifically used for: Patient visit data and cold-region TCM-specific data are input into a pre-trained TCM orthopedic auxiliary assessment model to obtain a TCM orthopedic auxiliary assessment report output by the model.

[0037] The TCM orthopedic auxiliary assessment report includes syndrome differentiation, pathogenesis analysis, disease severity, disease progression trend, prescription recommendations, physiotherapy recommendations, lifestyle adjustments, and special suggestions for cold regions.

[0038] The TCM orthopedic auxiliary assessment model includes a multi-dimensional feature extraction module, a cross-modal feature alignment module, a content recommendation engine based on a digital model library of bones from cold-region populations, and a TCM orthopedic auxiliary assessment engine.

[0039] In some embodiments, the multidimensional feature extraction module may include a text feature extraction layer and an image feature extraction layer; the text feature extraction layer architecture is set to a BERT-based fine-tuned model, which can extract text features from input medical records and other related texts; the image feature extraction layer architecture is set to a ResNet-50 pre-trained model, which can extract features from input medical images and other images; the cross-modal feature alignment module includes a multimodal alignment network and an adaptive feature mapping layer, wherein the multimodal alignment network uses contrastive learning and includes multiple projection heads (respectively for patient consultation data and cold-region TCM-specific data); The adaptive feature mapping layer is based on Transformer-based adaptive mapping, which can dynamically adjust the weights of different modal features. The contrastive learning loss uses the InfoNCE loss function. The content recommendation engine and TCM orthopedic auxiliary assessment engine based on the cold-region population skeletal digital model library can output corresponding content based on graph neural networks. The graph neural network can use the graph attention network GAT to process the cold-region population skeletal digital model library to perform TCM orthopedic auxiliary assessment (syndrome differentiation, pathogenesis analysis, disease severity) and content recommendation (disease development trend, prescription recommendation, physiotherapy plan recommendation, lifestyle adjustment recommendation, cold-region-specific suggestions).

[0040] In some embodiments, the intelligent assisted evaluation module is specifically used for: Patient visit data and cold-region-specific orthopedic health data are input into a pre-trained orthopedic health management model to obtain an orthopedic health management plan output by the model.

[0041] The orthopedic health management plan includes orthopedic disease risk assessment results, exercise plan, nutrition plan, and cold-region orthopedic disease prevention plan.

[0042] The orthopedic health management model includes a multi-dimensional feature extraction module, a cross-modal feature alignment module, a content recommendation engine based on a digital model library of bones from cold-region populations, and an orthopedic health management engine.

[0043] In some embodiments, the multidimensional feature extraction module may include a text feature extraction layer and an image feature extraction layer; the text feature extraction layer is configured as a BERT-based fine-tuned model, capable of extracting text features from input medical records and other related texts; the image feature extraction layer is configured as a ResNet-50 pre-trained model, capable of extracting features from input medical images and other images; the cross-modal feature alignment module includes a multimodal alignment network and an adaptive feature mapping layer; the multimodal alignment network uses contrastive learning and includes multiple projection heads (for patient consultation data and cold-region orthopedic health-specific data, respectively); the adaptive feature mapping layer is based on Transformer-based adaptive mapping, which can dynamically adjust the weights of different modal features, and the contrastive learning loss uses the InfoNCE loss function; the content recommendation engine and orthopedic health management engine based on the cold-region population skeletal digital model library can output corresponding content based on a graph neural network; the graph neural network can use a graph attention network (GAT) to process the cold-region population skeletal digital model library for orthopedic health management (orthopedic disease risk assessment results) and content recommendation (exercise programs, nutrition programs, and cold-region orthopedic disease prevention programs).

[0044] In some embodiments, the intelligent assisted evaluation module is specifically used for: Patient visit data and cold-region-specific orthopedic trauma data are input into a pre-trained orthopedic trauma auxiliary assessment model to obtain an orthopedic trauma auxiliary assessment report output by the model. The orthopedic trauma auxiliary assessment report includes the type of orthopedic trauma, the orthopedic trauma coping plan, rehabilitation suggestions, and cold-region-specific suggestions.

[0045] The orthopedic trauma auxiliary assessment model includes a multi-dimensional feature extraction module, a cross-modal feature alignment module, a content recommendation engine based on a digital model library of bones from cold-region populations, and an orthopedic trauma auxiliary assessment engine.

[0046] In some embodiments, the multidimensional feature extraction module may include a text feature extraction layer and an image feature extraction layer; the text feature extraction layer is configured as a BERT-based fine-tuned model, capable of extracting text features from input medical records and other related texts; the image feature extraction layer is configured as a ResNet-50 pre-trained model, capable of extracting features from input medical images and other images; the cross-modal feature alignment module includes a multimodal alignment network and an adaptive feature mapping layer; the multimodal alignment network uses contrastive learning and includes multiple projection heads (for patient consultation data and cold-region orthopedic trauma-specific data, respectively); the adaptive feature mapping layer is based on Transformer-based adaptive mapping, which can dynamically adjust the weights of different modal features, and the contrastive learning loss uses the InfoNCE loss function; the content recommendation engine and orthopedic trauma auxiliary assessment engine based on the cold-region population skeletal digital model library can output corresponding content based on a graph neural network; the graph neural network can use a graph attention network (GAT) to process the cold-region population skeletal digital model library for orthopedic trauma auxiliary assessment (orthopedic trauma type, orthopedic trauma coping strategy) and content recommendation (rehabilitation suggestions, cold-region-specific suggestions).

[0047] For intelligent surgical planning module, Figure 5 This is a schematic diagram of the interface of the preoperative planning software in the cold-region orthopedic digital diagnosis and treatment system provided in one embodiment of this application.

[0048] In some embodiments, the intelligent surgical planning module is specifically used for: A three-dimensional model of the knee joint is obtained by performing three-dimensional reconstruction based on the acquired medical images of the knee joint. Preoperative planning is performed based on a three-dimensional model of the knee joint to obtain an initial preoperative planning scheme for knee replacement. Based on cold-region-specific data associated with total knee arthroplasty, the initial preoperative planning scheme for knee arthroplasty was optimized to obtain the optimized preoperative planning scheme. After performing a simulated surgery based on the optimized preoperative planning scheme, postoperative motion simulation of the knee joint was conducted to determine whether various knee joint motion simulations could achieve the corresponding normal joint range of motion. If at least one knee joint motion simulation fails to achieve the corresponding normal joint range of motion, the optimized preoperative planning scheme will be adjusted until a target preoperative planning scheme that meets the motion simulation requirements is obtained.

[0049] In some embodiments, when optimizing the initial preoperative planning scheme for knee replacement based on cold-region-specific data associated with total knee replacement, osteoporotic areas can be marked based on bone quality data of the femur and tibia (e.g., areas with HU < 150), and the osteotomy angle, prosthesis type and size can be adjusted according to the distribution of osteoporotic areas to obtain an optimized scheme.

[0050] In some embodiments, when performing a simulated surgery on the knee joint after the optimized preoperative planning scheme, three surgical schemes can be simulated simultaneously. The first surgical scheme is the initial preoperative planning scheme for knee replacement without optimization; the second surgical scheme is the planning scheme optimized by the above parameters (osteotomy angle, prosthesis type and size, etc.); and the third surgical scheme is the reference surgical scheme obtained by surgical planning after osteoporosis fixation using bone cement or other means. By simulating and comparing the above three surgical schemes, the target preoperative planning scheme most suitable for the patient can be obtained.

[0051] In the process of motion simulation, finite element analysis can be used to assess the stress on the prosthesis and the holding force of the screw in the osteoporotic area to evaluate the impact of osteoporosis on the placement of the prosthesis, and to adjust and optimize the parameters accordingly when optimizing the surgical plan in the future.

[0052] In this way, by generating the above three surgical planning schemes and verifying and comparing them through motion simulation, we can make a horizontal comparison of the three surgical planning approaches: not considering the impact of osteoporosis, adjusting parameters to consider the impact of osteoporosis, and fixing osteoporosis before surgical planning. This will result in a surgical planning scheme that is more suitable for the patient's actual bone condition, thereby improving the patient's final surgical outcome.

[0053] In some embodiments, the intelligent surgical planning module is specifically used for: A three-dimensional model of the hip joint is obtained by performing three-dimensional reconstruction based on the acquired medical images of the hip joint. Preoperative planning is performed based on a three-dimensional model of the hip joint to obtain an initial preoperative planning scheme for hip replacement. Based on cold-region-specific data associated with total hip arthroplasty, the initial preoperative planning scheme for hip arthroplasty was optimized to obtain the optimized preoperative planning scheme. After performing a simulated surgery based on the optimized preoperative planning scheme, postoperative motion simulation of the hip joint was conducted to determine whether various hip joint motion simulations could achieve the corresponding normal joint range of motion. If at least one hip joint motion simulation fails to achieve the corresponding normal joint range of motion, the optimized preoperative planning scheme will be adjusted until a target preoperative planning scheme that meets the motion simulation requirements is obtained.

[0054] In some embodiments, when optimizing the initial preoperative planning scheme for knee replacement based on cold-region-specific data associated with total hip replacement, osteoporotic areas can be marked based on bone quality data of the femur and acetabulum (e.g., areas with HU < 150), and the press-fit area, prosthesis type and size can be adjusted according to the distribution of osteoporotic areas to obtain an optimized scheme.

[0055] In some embodiments, when performing postoperative motion simulation of the hip joint after a simulated surgery based on an optimized preoperative planning scheme, three surgical schemes can be simulated simultaneously. The first surgical scheme is the initial preoperative planning scheme for hip replacement without optimization; the second surgical scheme is the planning scheme optimized by the above parameters (press fit area, prosthesis type and size, etc.); and the third surgical scheme is the reference surgical scheme obtained by surgical planning after osteoporosis fixation using bone cement or other means. By performing motion simulation and comparing the above three surgical schemes, the target preoperative planning scheme most suitable for the patient can be obtained.

[0056] In the process of motion simulation, finite element analysis can be used to assess the stress on the prosthesis and the holding force of the screw in the osteoporotic area to evaluate the impact of osteoporosis on the placement of the prosthesis, and to adjust and optimize the parameters accordingly when optimizing the surgical plan in the future.

[0057] In this way, by generating the above three surgical planning schemes and verifying and comparing them through motion simulation, we can make a horizontal comparison of the three surgical planning approaches: not considering the impact of osteoporosis, adjusting parameters to consider the impact of osteoporosis, and fixing osteoporosis before surgical planning. This will result in a surgical planning scheme that is more suitable for the patient's actual bone condition, thereby improving the patient's final surgical outcome.

[0058] In some embodiments, the intelligent surgical planning module is specifically used for: A three-dimensional model of the knee joint is obtained by performing three-dimensional reconstruction based on the acquired medical images of the knee joint. Preoperative planning was conducted based on a three-dimensional model of the knee joint to obtain an initial preoperative planning scheme for unicompartmental arthroplasty. Based on cold-region-specific data associated with unicompartmental arthroplasty, the initial preoperative planning scheme for unicompartmental arthroplasty was optimized to obtain the optimized preoperative planning scheme. After performing a simulated surgery based on the optimized preoperative planning, postoperative motion simulation of the knee joint was conducted to determine whether various motion simulations could achieve the corresponding normal joint range of motion. If at least one of the motion simulations fails to achieve the corresponding normal joint range of motion, the optimized preoperative planning scheme will be adjusted until a target preoperative planning scheme that satisfies the motion simulation requirements is obtained.

[0059] In some embodiments, when optimizing the initial preoperative planning scheme for unicompartmental arthroplasty based on cold-region-specific data associated with unicompartmental arthroplasty, osteoporotic areas can be marked based on tibial bone quality data (e.g., areas with HU < 150), and the osteotomy angle, prosthesis type, and size can be adjusted according to the distribution of osteoporotic areas to obtain an optimized scheme.

[0060] In some embodiments, after a simulated surgery based on an optimized preoperative planning scheme, when performing postoperative motion simulation on the knee joint, three surgical schemes can be simulated simultaneously. The first surgical scheme is the initial preoperative planning scheme for unicompartmental arthroplasty without optimization; the second surgical scheme is the planning scheme optimized by the above parameters (osteotomy angle, prosthesis type and size, etc.); and the third surgical scheme is the reference surgical scheme obtained by surgical planning after osteoporosis fixation using bone cement or other means. By performing motion simulation and comparing the above three surgical schemes, the target preoperative planning scheme most suitable for the patient can be obtained.

[0061] In the process of motion simulation, finite element analysis can be used to assess the stress on the prosthesis and the holding force of the screw in the osteoporotic area to evaluate the impact of osteoporosis on the placement of the prosthesis, and to adjust and optimize the parameters accordingly when optimizing the surgical plan in the future.

[0062] In this way, by generating the above three surgical planning schemes and verifying and comparing them through motion simulation, we can make a horizontal comparison of the three surgical planning approaches: not considering the impact of osteoporosis, adjusting parameters to consider the impact of osteoporosis, and fixing osteoporosis before surgical planning. This will result in a surgical planning scheme that is more suitable for the patient's actual bone condition, thereby improving the patient's final surgical outcome.

[0063] In some embodiments, the intelligent surgical planning module is specifically used for: A three-dimensional model of the hip joint is obtained by performing three-dimensional reconstruction based on the acquired medical images of the hip joint. Based on the three-dimensional model of the hip joint, an initial preoperative planning scheme for periacetabular osteotomy was obtained. Based on cold-region-specific data associated with periacetabular osteotomy, the initial preoperative planning scheme for knee replacement was optimized to obtain the optimized preoperative planning scheme. After performing a simulated surgery based on the optimized preoperative planning scheme, postoperative motion simulation of the hip joint was conducted to determine whether various motion simulations could achieve the corresponding normal joint range of motion. If at least one of the motion simulations fails to achieve the corresponding normal joint range of motion, the optimized preoperative planning scheme will be adjusted until a target preoperative planning scheme that satisfies the motion simulation requirements is obtained.

[0064] In some embodiments, when optimizing the initial preoperative planning scheme for periacetabular osteotomy based on cold-region-specific data associated with periacetabular osteotomy, osteoporotic areas can be marked based on hip joint bone data (e.g., areas with HU < 150), and the osteotomy angle, correction angle, and internal fixation screw trajectory can be adjusted according to the distribution of osteoporotic areas to obtain an optimized scheme.

[0065] In some embodiments, when simulating postoperative movement of the hip joint after a simulated surgery based on an optimized preoperative planning scheme, three surgical schemes can be simulated simultaneously. The first surgical scheme is the initial preoperative planning scheme of periacetabular osteotomy without optimization; the second surgical scheme is the planning scheme optimized by the above parameters (osteotomy angle, correction angle, internal fixation screw trajectory); and the third surgical scheme is the reference surgical scheme obtained by surgical planning after osteoporosis fixation using bone cement or other means. By simulating and comparing the above three surgical schemes, the target preoperative planning scheme most suitable for the patient can be obtained.

[0066] In the process of motion simulation, finite element analysis can be used to assess the screw holding force in osteoporotic areas to evaluate the impact of osteoporosis on the trajectory of internal fixation screws after correction, and parameters can be adjusted and optimized accordingly when optimizing the surgical plan.

[0067] In this way, by generating the above three surgical planning schemes and verifying and comparing them through motion simulation, we can make a horizontal comparison of the three surgical planning approaches: not considering the impact of osteoporosis, adjusting parameters to consider the impact of osteoporosis, and fixing osteoporosis before surgical planning. This will result in a surgical planning scheme that is more suitable for the patient's actual bone condition, thereby improving the patient's final surgical outcome.

[0068] In some embodiments, the intelligent surgical planning module is specifically used for: Three-dimensional reconstruction is performed on the acquired medical images of the joint to obtain a three-dimensional model of the joint; Preoperative planning is carried out based on the three-dimensional model of the joint to obtain the initial preoperative planning scheme for sports medicine. Based on cold-region-specific data associated with sports medicine, the initial preoperative planning scheme for sports medicine was optimized to obtain an optimized preoperative planning scheme. After performing a simulated surgery based on the optimized preoperative planning scheme, postoperative motion simulation of the joint was conducted to determine whether various motion simulations could achieve the corresponding normal joint range of motion. If at least one of the motion simulations fails to achieve the corresponding normal joint range of motion, the optimized preoperative planning scheme will be adjusted until a target preoperative planning scheme that satisfies the motion simulation requirements is obtained.

[0069] In some embodiments, when optimizing the preoperative planning scheme for sports medicine based on cold-region-specific data associated with sports medicine, osteoporotic areas can be marked based on bone quality data of the femur and tibia (e.g., areas with HU < 150), and the location, angle, and diameter of the femoral / tibial tunnel can be adjusted according to the distribution of osteoporotic areas to obtain the optimized scheme.

[0070] In some embodiments, when performing a simulated surgery based on an optimized preoperative planning scheme and then simulating postoperative joint movement, three surgical plans can be simulated simultaneously. The first surgical plan is the initial preoperative planning scheme in sports medicine that has not been optimized; the second surgical plan is the planning scheme optimized by the above parameters (femoral / tibial tunnel position, angle, and diameter); and the third surgical plan is the reference surgical plan obtained by surgical planning after osteoporosis fixation using bone cement or other means. By simulating and comparing the above three surgical plans, the target preoperative planning scheme most suitable for the patient can be obtained.

[0071] In the process of motion simulation, finite element analysis can be used to assess the biomechanics (such as graft tension at different bending angles) in osteoporotic areas to evaluate the impact of osteoporosis on graft tension, and parameters can be adjusted and optimized accordingly when optimizing surgical plans in the future.

[0072] In this way, by generating the above three surgical planning schemes and verifying and comparing them through motion simulation, we can make a horizontal comparison of the three surgical planning approaches: not considering the impact of osteoporosis, adjusting parameters to consider the impact of osteoporosis, and fixing osteoporosis before surgical planning. This will result in a surgical planning scheme that is more suitable for the patient's actual bone condition, thereby improving the patient's final surgical outcome.

[0073] In some embodiments, the intelligent surgical planning module is specifically used for: A three-dimensional model of the spine is obtained by performing three-dimensional reconstruction based on the acquired medical images of the spine. Preoperative planning is performed based on a three-dimensional model of the spine to obtain an initial preoperative planning scheme for the spine. Based on cold-region-specific data associated with the spine, the initial preoperative planning scheme for the spine was optimized to obtain the optimized preoperative planning scheme. After performing a simulated surgery based on the optimized preoperative planning scheme, postoperative motion simulation of the spine was conducted to determine whether various motion simulations could achieve the corresponding normal joint range of motion. If at least one of the motion simulations fails to achieve the corresponding normal joint range of motion, the optimized preoperative planning scheme will be adjusted until a target preoperative planning scheme that satisfies the motion simulation requirements is obtained.

[0074] In some embodiments, when optimizing the initial preoperative planning scheme for the spine based on cold-region-specific data associated with the spine, osteoporotic areas can be marked based on the bone quality data of the spine (e.g., areas with HU < 150), and the screw trajectory, bone graft volume, and nerve root protection area can be adjusted according to the distribution of osteoporotic areas to obtain an optimized scheme.

[0075] In some embodiments, when performing postoperative motion simulation of the spine after a simulated surgery based on an optimized preoperative planning scheme, three surgical schemes can be simulated simultaneously. The first surgical scheme is the initial preoperative planning scheme of the spine without optimization; the second surgical scheme is the planning scheme optimized by the above parameters (screw trajectory, bone graft volume, nerve root protection area); and the third surgical scheme is the reference surgical scheme obtained by surgical planning after osteoporosis fixation using bone cement or other means. By performing motion simulation and comparing the above three surgical schemes, the target preoperative planning scheme most suitable for the patient can be obtained.

[0076] In the process of motion simulation, finite element analysis can be used to assess screw holding force and nerve root pressure in osteoporotic areas to evaluate the impact of osteoporosis on screw trajectory and nerve root pressure, and to adjust and optimize parameters accordingly when optimizing surgical plans in the future.

[0077] In this way, by generating the above three surgical planning schemes and verifying and comparing them through motion simulation, we can make a horizontal comparison of the three surgical planning approaches: not considering the impact of osteoporosis, adjusting parameters to consider the impact of osteoporosis, and fixing osteoporosis before surgical planning. This will result in a surgical planning scheme that is more suitable for the patient's actual bone condition, thereby improving the patient's final surgical outcome.

[0078] Figure 5 This is a schematic diagram of the interface of the operating software in the digital diagnosis and treatment system for all orthopedics in cold regions provided in one embodiment of this application.

[0079] In some embodiments, the intelligent surgical planning module is specifically used for: Based on the registration of at least two identical medical images of the acquired trauma site, a registered medical image of the trauma site is obtained. An intraoperative planning interface containing each registered medical image of the trauma site is presented. The intraoperative planning interface includes an osteoporosis risk area generated based on bone data of the trauma site. In response to a screw placement planning operation for any medical image, the demonstration effect of the screw placement planning operation in each medical image is presented collaboratively in the intraoperative planning interface to determine a trauma surgery planning scheme including screw placement planning.

[0080] For intelligent robot modules, The intelligent robot module is used to control surgical robots, such as embodied intelligent robots, used to perform surgery.

[0081] In some embodiments, the intelligent robot module is specifically used for: Based on intraoperative perception data, preoperative surgical plans, and pre-trained surgical robot decision-making and execution models, surgical robot operation decisions and control commands are generated in real time; among them, The surgical robot decision and execution model includes a surgical decision branch and a robot execution branch. The surgical decision branch is used to generate surgical robot operation decisions in real time based on intraoperative perception data and preoperative surgical plans. The robot execution branch is used to generate surgical robot control commands based on the surgical robot operation decisions.

[0082] Figure 6 This is a schematic diagram of the architecture of the surgical robot decision-making and execution model in the cold-region orthopedic digital diagnosis and treatment system provided in one embodiment of this application.

[0083] The surgical robot decision-making and execution model includes a multimodal feature extraction module, a surgical plan semantic encoder, a feature fusion module, a surgical decision branch, a robot execution branch, and a safety monitoring module.

[0084] The multimodal feature extraction module is used to extract features from intraoperative perception data, which includes patient physiological data, real-time audio data, real-time video data, surgical instrument tracking data, force sensor data, surgical robot status data, etc. For intraoperative perception data of different modalities, a modality-matching feature extractor can be used for feature extraction. For example, video data can be extracted using feature extraction networks with visual feature extraction capabilities, such as MobileNetV3-Small. The surgical plan semantic encoder can be extracted using a feature extractor with structured data feature extraction capabilities, and its model architecture can be, for example, GNN.

[0085] The feature fusion module can employ a network model with contextual semantic fusion capabilities. Its input consists of the output features of the surgical plan semantic encoder and the multimodal feature extraction module, which fuse the surgical plan and intraoperative perception data to output a 512-dimensional context vector. The surgical decision branch can be structured as a 2-layer BiLSTM + classification head + regression head, with the fused context vector as its input. It is used to output the action category and its confidence level, and can simultaneously output an attention heatmap and decision basis text to enhance the interpretability and safety of the surgical robot operation. The robot execution branch receives the robot's current state (including pose and other state data), an environmental obstacle map (the current operating room environment), and the target pose (i.e., the next motion target) corresponding to the action category output by the surgical decision branch. It outputs control commands, which may include 10 frames of look-ahead trajectory points (each point containing joint angles and end-effector operation parameters such as tool opening and closing) plus real-time velocity commands. The robot execution branch may include an obstacle perception module, a trajectory planner, a neural IK solver, and an adaptive controller. The obstacle perception module can be based on a lightweight PointNet architecture to detect obstacles in the surgical field of interest. For perception, the trajectory planner can adopt ConditionalVAE, with both its encoding structure and decoding results using LSTM. Its input is the current pose + moving target + obstacle, and the output is the planned look-ahead trajectory points. The neural IK solver architecture can adopt MLP, which converts the Cartesian pose in Cartesian coordinates into joint angles to obtain joint angle parameters for controlling the movement of the robotic arm. The adaptive controller can adopt LSTM-PID, which is used to perform adaptive control based on the current joint angle, target angle, error integral, and force feedback data, and outputs joint velocity correction to achieve adaptive adjustment based on real-time intraoperative situational awareness.

[0086] The safety monitoring module is embedded in the overall architecture through hard constraints. It can implement safety constraints for the surgical robot through real-time collision detection of trajectory points, joint velocity / acceleration limiting, and force control mode (resistance control is triggered when the force exceeds a threshold). The safety monitoring module can be implemented with independent hardware to ensure the safety of surgical robot operation. For example, safety monitoring can be implemented through FPGA + independent MCU to physically isolate it from the surgical decision branch and robot execution branch. The safety monitoring module can send hard interrupt signals to the surgical decision branch and robot execution branch to achieve safety protection when an anomaly is detected. The robot execution branch can provide real-time feedback on the execution status to the surgical decision branch so that the surgical decision branch can be aware of the robot's execution status in real time.

[0087] In some embodiments, the intelligent robot module is specifically used for: Based on the control modes corresponding to each surgical stage planned in the preoperative plan and the intraoperative sensing data, the surgical robot is controlled to assist in performing surgical operations according to the corresponding control modes. The control modes of surgical robots include local control, remote control, and autonomous control.

[0088] Specifically, during the preoperative planning stage, control modes corresponding to each surgical stage can be planned based on the surgeon's proficiency and success rate in each surgical procedure. During the operation, the surgical robot is controlled according to the corresponding control mode as it progresses to the corresponding surgical stage.

[0089] Figure 7 This is a schematic diagram of the intelligent control decision-making architecture in a digital and intelligent diagnosis and treatment system for all orthopedics in cold regions provided in one embodiment of this application.

[0090] In some embodiments, the intelligent robot module is specifically used for: In response to meeting the conditions for updating the control mode of the surgical robot, the control mode of the surgical robot is updated in real time; wherein... Entering the target surgical stage, performing the target surgical procedure, remote connection interrupted, receiving a control mode switching command.

[0091] Specifically, when entering the target surgical stage, the system can switch between local control and remote or autonomous control, between remote control and local or autonomous control, and between autonomous control and local or remote control; when performing the target surgical operation, the system can switch between local control and remote or autonomous control, between remote control and local or autonomous control, and between autonomous control and local or remote control; in the event of a remote connection interruption, the system can switch between remote control and local or autonomous control; and upon receiving a control mode switching command, the system can switch between local control and remote or autonomous control, between remote control and local or autonomous control, and between autonomous control and local or remote control.

[0092] In some embodiments, the intelligent robot module is specifically used for: Determine the current surgical stage based on intraoperative sensory data; Based on the surgical procedure guidelines corresponding to the current surgical stage, provide surgical procedure guidelines.

[0093] In some embodiments, the intelligent robot module is specifically used for: Intraoperative perception data and preoperative surgical plans are input into a pre-trained intelligent surgical collaborative decision-making model to obtain real-time surgical operation suggestions output by the intelligent surgical collaborative decision-making model. Intraoperative perception data includes patient physiological data, real-time surgical audio and video data, and surgical instrument tracking data.

[0094] The intraoperative perception data includes patient physiological data, real-time surgical audio and video data, and surgical instrument tracking data. The intelligent surgical collaborative decision-making model is a generative model capable of processing real-time serialized data. The input of the intelligent surgical collaborative decision-making model includes serialized intraoperative perception data and prompt information. The prompt information may include intraoperative interaction requirements (such as confirming the current surgical progress, estimating the remaining surgical time, etc.).

[0095] The output of the intelligent surgical collaborative decision-making model includes real-time intraoperative prompts, intraoperative operation suggestions, and surgical progress predictions; among which... The model architecture of the intraoperative real-time alert module can be a CNN+BiLSTM+Attention mechanism. The number of CNN convolutional kernels can be 32 to extract local features of vital signs; the kernel size can be 3*3 to optimize feature extraction; the number of BiLSTM hidden units can be set to 64 to handle temporal data; the number of Attention heads can be set to 8 to optimize multi-dimensional feature fusion; the loss function can be set to a weighted cross-entropy loss function to focus on identifying high-risk events (high-risk surgical procedures, etc.); the optimizer can be set to AdamW to improve the convergence speed during training; and the learning rate can be set to 0.001 to control the learning speed.

[0096] The model architecture of the intraoperative operation suggestion module can be DQN + expert knowledge base. It generates initial surgical suggestions based on DQN and filters and sorts them according to the expert knowledge base to output high-value surgical operation suggestions. The state space dimension can be set to 50, which includes surgical stage, vital signs, risk level, etc.; the action space size can be set to 100, which is used to define the number of possible operation suggestions; the discount factor can be set to 0.95 to encourage future reward weights; the learning rate can be set to 0.001 to control the learning speed; the experience replay buffer size can be set to 100,000 to store historical experience; the batch size can be set to 64; and the target network update frequency can be set to 100 to balance training effect and training efficiency.

[0097] The model architecture for the surgical progress prediction module can be an LSTM + Attention mechanism, which can predict the remaining time based on historical data, adjust the prediction according to the current risk level, and generate a confidence interval. The LSTM hidden units can be set to 128 for temporal modeling; the number of Attention heads can be set to 4 for feature fusion; the sliding window size can be dynamically adjusted according to the surgical type, for example, it can be set to 30 minutes; the prediction step size can be set to 5 minutes; and the loss function can be set to MAE to evaluate the prediction accuracy.

[0098] In some embodiments, the intelligent robot module may also determine the current surgical progress based on intraoperative perception data in response to the fulfillment of surgical progress confirmation conditions; wherein, the surgical progress confirmation conditions include entering the target surgical stage, performing the target surgical operation, and receiving a surgical progress confirmation instruction.

[0099] For remote modules, Figure 8 This is a schematic diagram of the architecture of the remote module in the cold-region orthopedic digital diagnosis and treatment system provided in one embodiment of this application.

[0100] In some embodiments, the remote module is specifically used for: The user's remote diagnosis and treatment data is input into a pre-trained intelligent pre-assessment model to obtain the pre-assessment results output by the intelligent pre-assessment model.

[0101] The intelligent pre-assessment model includes an attribute feature extraction module, a historical feature extraction module, a real-time feature extraction module, a feature fusion module, and multiple output modules; each output module is used to output the probability information of the user currently having various preset categories of orthopedic diseases.

[0102] Figure 9 This is a schematic diagram of the architecture of remote diagnosis and treatment in a cold-region orthopedic digital diagnosis and treatment system provided in one embodiment of this application, which incorporates a digital bone model library for people in cold regions.

[0103] In some embodiments, the attribute feature extraction module included in the intelligent pre-evaluation model can be composed of two MLP layers, with the hidden layer sizes set to 64 and 32 respectively, the L2 weight decay of the output stage being 0.001 to improve generalization, the activation function being set to the ReLU function, the training batch being set to 32 to balance memory and efficiency, and the output being a 32-dimensional feature vector.

[0104] In some embodiments, the historical feature extraction module included in the intelligent pre-evaluation model may consist of a text encoder, an image encoder, a test data MLP, a medication record MLP, and a fusion submodule; wherein, the input of the text encoder can be a text-based evaluation / surgical record, and the text encoder can be the encoder in a pre-trained medical BERT model, with the output dimension of the text encoder set to 768; the input of the image encoder can be a medical image, and the type of image encoder can be a pre-trained ResNet network with fully connected layers removed (e.g., ResNet-50, ResNet-101, etc.). The output dimension of the encoder is set to 2048; the test data MLP can be composed of two MLP layers with hidden layer sizes of 64 and 32 respectively, and the activation function is set to LeakyReLU, outputting a 32-dimensional feature vector; the medication record MLP can be composed of two MLP layers with hidden layer sizes of 64 and 32 respectively, and the activation function is set to LeakyReLU, outputting a 32-dimensional feature vector; the fusion submodule is used to concatenate the outputs of the text encoder, image encoder, test data MLP, and medication record MLP, and perform dimensionality reduction through the MLP fusion layer, outputting a 128-dimensional feature vector.

[0105] In some embodiments, the real-time feature extraction module included in the intelligent pre-assessment model can be composed of a physiological branch and a psychological branch (used to model the correlation between psychological indicators such as depression, anxiety, and pain and orthopedic diseases); wherein, the model architecture of the physiological branch can be a CNN model capable of processing sequential data, which can be composed of sequentially concatenated convolutional layers, pooling layers, convolutional layers, pooling layers, fully connected layers, and activation layers, and the output dimension can be set to 64; the model architecture of the psychological branch can be an MLP, and the output dimension can be set to 64; the outputs of the physiological branch and the psychological branch can be compressed after concatenation to obtain the 64-dimensional features output by the real-time feature extraction module.

[0106] In some embodiments, the output of the intelligent pre-assessment model may include the probability of developing osteoporosis.

[0107] In some embodiments, the output of the intelligent pre-assessment model may include the probability of developing sports injuries.

[0108] In some embodiments, the output of the intelligent pre-assessment model may include the probability of developing osteoarthritis.

[0109] In some embodiments, the model architecture of the output module of the intelligent pre-evaluation model can be an MLP, which includes a fully connected layer and the probability range of the output value is [0,1].

[0110] In some embodiments, the remote module is specifically used for: A rehabilitation assessment is conducted based on the received remote rehabilitation data from the patient to determine the patient's current rehabilitation progress; wherein, the remote rehabilitation data from the patient includes exercise verification videos, medical imaging data, medical test data, and rehabilitation progress description information; Based on the deviation between the patient's current recovery progress and the estimated recovery progress, the patient's recovery plan is updated in real time in conjunction with data on the cold environment.

[0111] In some embodiments, postoperative rehabilitation management can be achieved through a large rehabilitation management model, which includes a rehabilitation progress assessment branch and a rehabilitation plan update branch. The rehabilitation progress assessment branch can be combined with a cold-region bone digital model library to assess rehabilitation progress, and the rehabilitation plan update branch can be combined with a cold-region bone digital model library to update the rehabilitation plan.

[0112] The digital model library of skeletal structures for people living in cold regions includes skeletal characteristics of people living in cold regions, norms of orthopedic diseases in cold regions, bone metabolism data specific to cold regions, bone health behavior data, cases of orthopedic diagnosis and treatment and postoperative recovery in cold regions, and bone health risk assessment and intervention programs.

[0113] The cold-region population skeletal digital model library can consist of data such as orthopedic patient cases, diagnosis and rehabilitation guidelines, patient rehabilitation records, and expert suggestions selected by experts. When building the cold-region population skeletal digital model library based on the above data, the above data can be converted into structured data and stored centrally to obtain a database-formatted cold-region population skeletal digital model library, which can be used for online diagnosis and treatment, personalized rehabilitation program generation, and orthopedic health management.

[0114] In some embodiments, when conducting rehabilitation assessments based on received remote rehabilitation data from patients to determine their current rehabilitation progress, a digital model library of cold-region bones can be used to assess the rehabilitation progress.

[0115] Specifically, the system can first match patients' remote rehabilitation data, identify target cases that match patients from the digital model library of skeletal structures of people in cold regions, determine the deviation between the patient's current rehabilitation progress and the estimated rehabilitation progress by using the rehabilitation progress included in the target cases, and update the patient's rehabilitation plan in real time by combining cold region environmental data, so as to achieve rehabilitation management for patients.

[0116] The above steps can be achieved through the generative function of the rehabilitation management big data model, and will not be explained in detail here.

[0117] In some embodiments, the remote module is specifically used for: During the live broadcast, live broadcast markers are generated based on intraoperative perception data to mark each surgical procedure; Based on the live broadcast tags and recorded surgical audio and video data, surgical teaching videos are generated; The intraoperative sensing data includes patient physiological data, real-time surgical audio and video data, and surgical instrument tracking data.

[0118] In some embodiments, intraoperative perception data, live broadcast markers, patient visit data, and the doctor's planned surgical procedure can be input into the surgical teaching video generation model to obtain the surgical teaching video output by the surgical teaching video generation model.

[0119] The patient's medical data includes historical assessment records, medical imaging data, historical medical test data, historical surgical data, historical medication data, and patient attribute information. The patient attribute information may include age, gender, weight, height, BMI, occupation, history of underlying diseases, and allergies. Historical assessment records may include descriptive assessment information, such as "left knee arthritis." Medical imaging data may include knee X-rays, MRI, CT scans, etc. Historical medical test data may include complete blood count data, blood biochemistry data, and urinalysis results. Historical surgical records may include surgical type, surgical time, postoperative rehabilitation records, and postoperative complication records. Historical medication records may include the name, dosage, frequency, and time of medication taken. The doctor's surgical plan may include the name of the surgical procedure, key surgical steps, expected surgical duration, and surgical approach selection. The initial surgical plan can be obtained from the electronic medical records uploaded by the doctor through structured data analysis.

[0120] The surgical teaching video generation model includes a multi-dimensional feature extraction module, a feature fusion and teaching logic engine, and a video generation and teaching enhancement module.

[0121] The multidimensional feature extraction module includes an intraoperative data encoder, a patient data encoder, and a planning scheme encoder. The intraoperative data encoder includes a video branch, an audio branch, and a text branch. The video branch uses 3D-CNN+Transformer, with the number of channels ranging from 64 to 128 to 256 (with 3*3*3 convolutional kernels). The audio branch uses ResNet-18+MFCC, with MFCC features set to 16 dimensions and a 30ms frame length. The ResNet-18 classifier identifies key sounds (including instrument sounds, alarm sounds, and surgical operation narration sounds) and outputs a voiceprint feature vector. The text branch uses MLP+Embedding to output a text feature vector, where the MLP is a 2-layer MLP (128 to 64 hidden layers) and word embedding is used to process the text. The patient visit data encoder uses MLP + Embedding to output the feature vector of the patient visit data. The MLP is a 2-layer MLP (128 to 64 hidden layers) and uses word embedding to process the text. The planning scheme encoder uses BERT-base to output the feature vector of the planning scheme.

[0122] The feature fusion and teaching logic engine includes a cross-modal feature alignment module, a teaching content planner, and a teaching rule engine based on a medical knowledge graph and rule base. The cross-modal feature alignment module uses Cross-Attention + temporal alignment loss to calculate the similarity of features extracted by the multi-dimensional feature extraction module. The loss function is set to L1 + temporal bias penalty (λ=0.3 to avoid distortion caused by over-alignment), the number of attention heads is set to 8, the number of hidden layers is set to 512, and the output is the aligned fused feature (1024 dimensions). The teaching rule engine based on the medical knowledge graph and rule base uses pre-made surgical rules (e.g., gallstones → perforation, to establish associations), generates teaching points based on doctors' historical surgical plans, and uses a graph neural network for rule updates. The teaching rule engine outputs a list of teaching points. The teaching content planner is used to output a video segmentation outline based on the input fused features and the list of teaching points. The architecture of the teaching content planner can be set to a Transformer Decoder with 4 layers, 512 hidden layers, and a learning rate of 1e-4 to avoid overfitting.

[0123] The video generation and instructional enhancement module includes a video generator, a quality optimizer, and an instructional enhancer. The video generator can be configured as a Diffusion Model + pre-trained video model. The pre-trained video model can be, for example, a medical-specific improved version of the Sora model, with a diffusion step of 50 and a Transformer model layer of 12. The output of the video generator is a sequence of video frames. The quality optimizer is used to optimize the video. Its architecture can adopt a GAN discriminator. The input is the original audio and video data + the sequence of video frames output by the video generator. The discriminator can be configured as a 4-layer CNN to calculate the realism score. The loss function during training can be set as L1 + GAN loss (with a weight of 0.7). The instructional enhancer is used to add annotations, subtitles, and narration to the video. Its architecture can be OCR + 3D annotation + TTS. OCR can add subtitles to the video, 3D annotation can add annotations to specific content in the video, such as highlighting blood vessels and organs, and TTS can generate AI instructional narration to enhance the instructional attributes.

[0124] In some embodiments, the remote module is specifically used for: When the surgical robot is an orthopedic surgical robot, in response to the remote control command of the console, the control information of the robotic arm is generated based on the pose information of the robotic arm and the pose information of the patient's osteotomy site. The control information is sent to the robotic arm to assist the surgeon in performing the operation.

[0125] In some embodiments, the remote module is specifically used for: In the scenario of intraoperative medical data retrieval, in response to the request for remote medical data retrieval, a medical data acquisition request is sent to a remote medical database via 5G, and the target medical data is received from the remote medical database so as to present the target medical data in real time during the operation; In the scenario of remote collaboration in pre-hospital emergency care, in response to emergency data collaboration requests, the system receives patient physiological data sent from the medical terminal in the emergency vehicle via 5G, and matches emergency surgical plans based on the patient physiological data, so as to prepare for emergency care according to the successfully matched target emergency surgical plan.

[0126] For postoperative rehabilitation modules, Figure 10 This is a schematic diagram of the architecture of the cold-region comprehensive orthopedic digital diagnosis and treatment system provided in one embodiment of this application, which manages the entire postoperative rehabilitation process based on a digital bone model library of cold-region populations.

[0127] In some embodiments, the postoperative rehabilitation module is specifically used for: The expected completion rate of the surgery is assessed by comparing the patient's postoperative medical imaging data with the preoperative planning scheme; and the surgical outcome is assessed by evaluating the patient's postoperative clinical indicators.

[0128] In the postoperative evaluation based on the patient's postoperative clinical indicators, similar cases in the cold region orthopedic diagnosis and treatment and postoperative recovery cases in the cold region population bone digital model library can be used to obtain the surgical effect evaluation results.

[0129] Specifically, matching can be performed based on patient attribute information and medical data to identify target cases that match the patient, and the surgical effect can be evaluated according to the postoperative clinical indicators included in the target cases.

[0130] In some embodiments, the postoperative rehabilitation module is specifically used for: Based on postoperative assessment results, patient attribute information, and medical records, an in-hospital rehabilitation plan tailored to the patient is generated; among which, The in-hospital rehabilitation program includes in-hospital nursing care, physical therapy, nutrition, exercise, and discharge criteria.

[0131] In some embodiments, the postoperative rehabilitation module is specifically used for: Based on postoperative assessment results, patient attribute information, and medical records, a matching outpatient rehabilitation plan is generated; among which, The outpatient rehabilitation program includes outpatient nursing care, physical therapy, nutrition, exercise, and cold-weather-specific rehabilitation recommendations.

[0132] In some embodiments, postoperative assessment results, patient attribute information, and medical data can be input into a pre-trained personalized rehabilitation plan generation model to obtain in-hospital rehabilitation plans and out-of-hospital rehabilitation plans output by the personalized rehabilitation plan generation model. The personalized rehabilitation plan generation model includes an attribute feature extraction module, a medical visit feature extraction module, a feature fusion module, an in-hospital rehabilitation plan output branch, and an out-of-hospital rehabilitation plan output branch.

[0133] In some embodiments, the attribute feature extraction module included in the personalized rehabilitation plan generation model can be composed of two MLP layers, with the hidden layer sizes set to 64 and 32 respectively, the L2 weight decay of the output stage being 0.001 to improve generalization, the activation function being set to the ReLU function, the training batch being set to 32 to balance memory and efficiency, and the output being a 32-dimensional feature vector.

[0134] In some embodiments, the personalized rehabilitation plan generation model includes a patient visit feature extraction module, which may consist of a text encoder, an image encoder, a laboratory data MLP, a medication record MLP, and a fusion submodule. The input to the text encoder can be a text-based assessment / surgical record (and postoperative assessment results), and the text encoder can be the encoder in a pre-trained medical BERT model, with an output dimension of 768. The input to the image encoder can be a medical image, and the image encoder type can be a pre-trained ResNet network with fully connected layers removed (e.g., ResNet-50, ResNet-10). The output dimension of the image encoder is set to 2048 (e.g., 1). The test data MLP can be composed of two MLP layers with hidden layer sizes of 64 and 32 respectively, and the activation function is set to LeakyReLU, outputting a 32-dimensional feature vector. The medication record MLP can also be composed of two MLP layers with hidden layer sizes of 64 and 32 respectively, and the activation function is set to LeakyReLU, outputting a 32-dimensional feature vector. The fusion submodule is used to concatenate the outputs of the text encoder, image encoder, test data MLP, and medication record MLP, and perform dimensionality reduction through the MLP fusion layer, outputting a 128-dimensional feature vector.

[0135] In some embodiments, the feature fusion module included in the personalized rehabilitation plan generation model takes as input a 32-dimensional feature vector output by the attribute feature extraction module and a 128-dimensional feature vector output by the medical visit feature extraction module, and then passes them through a concatenation process, a fully connected layer, and a Swish activation layer to obtain the output 128-dimensional fused feature vector.

[0136] Furthermore, the output branch of the in-hospital rehabilitation program includes multiple output modules, each of which is used to output in-hospital nursing plans, physiotherapy plans, nutrition plans, in-hospital exercise plans, and discharge criteria; the output branch of the out-of-hospital rehabilitation program includes multiple output modules, each of which is used to output out-of-hospital nursing plans, physiotherapy plans, nutrition plans, out-of-hospital exercise plans, and cold-region-specific rehabilitation suggestions.

[0137] Among them, the physiotherapy plan and nutrition plan can share the same output module, and the nursing plan and exercise plan can add some plan content based on cold-region-specific data on the same output module (the in-hospital rehabilitation plan branch adds the relevant in-hospital content, and the out-of-hospital rehabilitation plan branch adds the relevant out-of-hospital content) to achieve the reuse of the corresponding output modules (nursing plan and exercise plan).

[0138] In some embodiments, the personalized rehabilitation plan generation model includes a nutrition plan output module, which takes a fused feature vector as input and outputs a nutrition plan containing dietary recommendations. The model architecture of the nutrition plan output module includes an MLP classifier, and the number of output categories can be set to 20, and the number of hidden layers can be set to 64.

[0139] In some embodiments, when training a personalized rehabilitation plan generation model, the loss functions corresponding to each output module can be weighted to obtain a weighted total loss, and training can be performed based on the weighted total loss. According to clinical importance, the weight ratios corresponding to the output branches of in-hospital rehabilitation plans and out-of-hospital rehabilitation plans can be set to 3:2.

[0140] In some embodiments, the postoperative rehabilitation module is specifically used for: Based on the patient's in-hospital rehabilitation assessment data, simulate the patient's joint activity index and pain index under cold environment conditions, and assess whether the patient meets the discharge criteria under cold environment conditions based on the simulation results; If the patient meets the matching discharge criteria, a home rehabilitation assessment is conducted based on the patient's home temperature data and in-hospital rehabilitation assessment data to determine whether the patient meets the conditions for home rehabilitation.

[0141] In the process of conducting home rehabilitation assessments based on patients' home temperature data and in-hospital rehabilitation assessment data, similar cases from the cold-region orthopedic diagnosis and treatment and postoperative recovery cases in the cold-region population skeletal digital model database can be used to conduct postoperative assessments in order to obtain home rehabilitation assessment results.

[0142] Specifically, the patient's home temperature data and in-hospital rehabilitation assessment data can be matched to identify target cases that match the patient, and home rehabilitation assessments can be conducted according to the home rehabilitation recovery status included in the target cases.

[0143] In some embodiments, the postoperative rehabilitation module is further configured to: The rehabilitation assessment results are obtained based on medical images taken after rehabilitation training, exercise verification videos, and multimodal rehabilitation assessment models.

[0144] The multimodal rehabilitation assessment model includes an adapter module, a text encoder, a feature alignment and fusion module, and a task decoding module. The adapter module dynamically generates modality-specific parameters based on the modality of the input medical image, enabling the image encoder to process the corresponding modality of the medical image. The feature alignment and fusion module constructs a joint embedding space to align text features and image features at the semantic level, and then fuses the aligned text features and image features. The text encoder extracts features from the image labels corresponding to the input medical image. These image labels can be labels obtained after processing the medical image, such as subjective conclusions drawn by doctors after reviewing the medical image.

[0145] Figure 11 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown.

[0146] The electronic device may include a processor 1101 and a memory 1102 storing computer program instructions.

[0147] Specifically, the processor 1101 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0148] Memory 1102 may include mass storage for data or instructions. For example, and not limitingly, memory 1102 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 1102 may include removable or non-removable (or fixed) media. Where appropriate, memory 1102 may be internal or external to an electronic device. In a particular embodiment, memory 1102 may be a non-volatile solid-state memory.

[0149] In one embodiment, memory 1102 may be read-only memory (ROM). In one embodiment, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0150] The processor 1101 reads and executes computer program instructions stored in the memory 1102 to implement the functions of the cold-region orthopedic digital diagnosis and treatment system described in any of the above embodiments.

[0151] In one example, the electronic device may also include a communication interface 1103 and a bus 1110. For example, Figure 11 As shown, the processor 1101, memory 1102, and communication interface 1103 are connected through bus 1110 and complete communication with each other.

[0152] The communication interface 1103 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0153] Bus 1110 includes hardware, software, or both, that couples components of an electronic device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-E) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 1110 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, this application contemplates any suitable bus or interconnect.

[0154] Alternatively, embodiments of this application may be implemented using a computer-readable storage medium. This computer-readable storage medium stores computer program instructions; when executed by a processor, these computer program instructions implement the functions of the cold-region orthopedic digital intelligent diagnosis and treatment system described in any of the above embodiments.

[0155] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0156] The functional modules shown in the above-described block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0157] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0158] The aspects of this application have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by dedicated hardware performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0159] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A digital intelligent diagnosis and treatment system for orthopedics in cold regions, characterized in that, include: The intelligent auxiliary assessment module is used to conduct auxiliary assessment of all orthopedic diseases in cold regions based on patient visit data and cold-region-specific data. The intelligent surgical planning module is used to perform preoperative planning for hip and knee joint surgery, spinal surgery, sports medicine surgery, and trauma surgery based on patient medical data and cold-region-specific data. The intelligent robot module is used to respond to intraoperative interaction needs, control the equipment and perform voice interaction based on these needs, and provide real-time intraoperative prompts based on the preoperative surgical plan. The system generates surgical operation suggestions in real time during the operation and updates the surgical plan in real time based on the response results of the surgical operation suggestions, resulting in an updated real-time surgical plan. Based on the preoperative surgical plan and intraoperative sensory data, the surgical robot is controlled to assist in the execution of surgical operations; the control mode of the surgical robot is updated in real time. The remote module is used to perform a preliminary assessment based on the received remote medical data from the user and to feed the preliminary assessment results back to the user. Rehabilitation assessments are conducted based on received remote rehabilitation data from patients, and the rehabilitation plans for patients are updated in real time based on the assessment results and cold environment data; live surgical demonstrations are conducted, and surgical teaching videos are automatically generated based on the live broadcast content; surgical robots are controlled according to received remote surgical instructions to realize remote surgery; remote multidisciplinary consultations, intraoperative medical data retrieval, and remote pre-hospital emergency care collaboration are carried out. The postoperative rehabilitation module is used to conduct postoperative assessments based on patient postoperative data and preoperative planning, obtaining postoperative assessment results. Based on the postoperative assessment results, patient attribute information, and medical records, it generates personalized rehabilitation plans for the patient. These personalized rehabilitation plans include in-hospital and out-of-hospital rehabilitation plans, with the out-of-hospital plan including cold-climate-specific rehabilitation suggestions. The module simulates joint mobility and pain indicators under cold-climate conditions based on the patient's in-hospital rehabilitation assessment data to assess whether the patient meets the discharge criteria for cold-climate environments. Finally, it conducts rehabilitation assessments based on the patient's out-of-hospital rehabilitation assessment data, obtaining rehabilitation assessment results, and updates the out-of-hospital rehabilitation plan accordingly.

2. The digital intelligent diagnosis and treatment system for all orthopedics in cold regions according to claim 1, characterized in that, The intelligent auxiliary evaluation module is specifically used for: Patient medical data and cold-region sports injury-specific data are input into a pre-trained intelligent sports injury analysis model to obtain an intelligent sports injury analysis report output by the model. The sports injury intelligent analysis report includes the injury type, injury severity, risk assessment results, assessment recommendations, rehabilitation recommendations, and cold-weather-specific recommendations.

3. The digital intelligent diagnosis and treatment system for all orthopedics in cold regions according to claim 1 or 2, characterized in that, The intelligent auxiliary evaluation module is specifically used for: Patient medical data and cold-region-specific osteoporosis data are input into a pre-trained osteoporosis assessment model to obtain an osteoporosis auxiliary assessment report output by the osteoporosis assessment model. The osteoporosis auxiliary assessment report includes osteoporosis risk level, osteoporosis type prediction, fracture risk prediction, and personalized intervention recommendations.

4. The digital intelligent diagnosis and treatment system for all orthopedics in cold regions according to claim 1 or 2, characterized in that, The intelligent surgical planning module is specifically used for: A three-dimensional model of the knee joint is obtained by performing three-dimensional reconstruction based on the acquired medical images of the knee joint. Preoperative planning is performed based on a three-dimensional model of the knee joint to obtain an initial preoperative planning scheme for knee replacement. Based on bone data associated with total knee arthroplasty, the initial preoperative planning scheme for knee arthroplasty was optimized to obtain the optimized preoperative planning scheme. After performing a simulated surgery based on the optimized preoperative planning scheme, postoperative motion simulation of the knee joint was conducted to determine whether various knee joint motion simulations could achieve the corresponding normal joint range of motion. If at least one knee joint motion simulation fails to achieve the corresponding normal joint range of motion, the optimized preoperative planning scheme will be adjusted until a target preoperative planning scheme that meets the motion simulation requirements is obtained.

5. The digital intelligent diagnosis and treatment system for all orthopedics in cold regions according to claim 4, characterized in that, The intelligent surgical planning module is specifically used for: A three-dimensional model of the hip joint is obtained by performing three-dimensional reconstruction based on the acquired medical images of the hip joint. Based on the three-dimensional model of the hip joint, an initial preoperative planning scheme for periacetabular osteotomy was obtained. Based on bone data associated with periacetabular osteotomy, the initial preoperative planning scheme for knee replacement was optimized to obtain the optimized preoperative planning scheme. After performing a simulated surgery based on the optimized preoperative planning scheme, postoperative motion simulation of the hip joint was conducted to determine whether various motion simulations could achieve the corresponding normal joint range of motion. If at least one of the motion simulations fails to achieve the corresponding normal joint range of motion, the optimized preoperative planning scheme will be adjusted until a target preoperative planning scheme that satisfies the motion simulation requirements is obtained.

6. The digital intelligent diagnosis and treatment system for all orthopedics in cold regions according to claim 1, characterized in that, The intelligent robot module is specifically used for: Based on intraoperative perception data, preoperative surgical plans, and pre-trained surgical robot decision-making and execution models, surgical robot operation decisions and control commands are generated in real time; among them, The surgical robot decision and execution model includes a surgical decision branch and a robot execution branch. The surgical decision branch is used to generate surgical robot operation decisions in real time based on intraoperative perception data and preoperative surgical plans. The robot execution branch is used to generate surgical robot control commands based on the surgical robot operation decisions.

7. The digital intelligent diagnosis and treatment system for all orthopedics in cold regions according to claim 1, characterized in that, The intelligent robot module is specifically used for: Based on the control modes corresponding to each surgical stage planned in the preoperative plan and the intraoperative sensing data, the surgical robot is controlled to assist in performing surgical operations according to the corresponding control modes. The control modes of surgical robots include local control, remote control, and autonomous control.

8. The digital intelligent diagnosis and treatment system for all orthopedics in cold regions according to claim 1, characterized in that, The remote module is specifically used for: A rehabilitation assessment is conducted based on the received remote rehabilitation data from the patient to determine the patient's current rehabilitation progress; wherein, the remote rehabilitation data from the patient includes exercise verification videos, medical imaging data, medical test data, and rehabilitation progress description information; Based on the deviation between the patient's current recovery progress and the estimated recovery progress, the patient's recovery plan is updated in real time in conjunction with data on the cold environment.

9. The digital intelligent diagnosis and treatment system for all orthopedics in cold regions according to claim 1, characterized in that, The postoperative rehabilitation module is specifically used for: Based on postoperative assessment results, patient attribute information, and medical records, an in-hospital rehabilitation plan tailored to the patient is generated; among which, The in-hospital rehabilitation program includes in-hospital nursing care, physical therapy, nutrition, exercise, and discharge criteria.

10. The digital intelligent diagnosis and treatment system for all orthopedics in cold regions according to claim 9, characterized in that, The postoperative rehabilitation module is specifically used for: Based on the patient's in-hospital rehabilitation assessment data, simulate the patient's joint activity index and pain index under cold environment conditions, and assess whether the patient meets the discharge criteria under cold environment conditions based on the simulation results; If the patient meets the matching discharge criteria, a home rehabilitation assessment is conducted based on the patient's home temperature data and in-hospital rehabilitation assessment data to determine whether the patient meets the conditions for home rehabilitation.

Images