Artificial intelligence assisted spine health monitoring system

Abstract

The invention discloses an artificial intelligence assisted spine health monitoring system, and belongs to the technical field of health monitoring equipment, and the system comprises a spine health monitoring suit module which is used for collecting spine three-dimensional motion signals when a subject executes different spine motion modes; the artificial intelligence module is used for analyzing the spine three-dimensional motion signal based on a deep learning algorithm so as to judge the health condition of the subject; the cloud center management module is used for storing the spine three-dimensional motion signals collected by the spine health monitoring suit module and the health condition judgment result, obtained by the artificial intelligence module, of the subject; and generating health monitoring data of the subject. The technical problems that an existing spine health screening technology is low in screening sensitivity, poor in monitoring continuity and low in intelligent degree can be solved.

Description

Technical Field

[0001] The present invention relates to the technical field of health monitoring equipment, and in particular to an artificial intelligence-assisted spinal health monitoring system. Background Art

[0002] Spinal deformity refers to the deviation of the spine from its normal position in the coronal, sagittal, and axial positions. Clinically, it mainly manifests as a variety of complex deformities such as lateral, posterior, lordotic, and rotational deformities, and the anatomical structures involved are extremely complex. Among them, scoliosis is the most common type of spinal deformity. Clinically, scoliosis refers to a lateral curvature of the spine in the sagittal plane greater than 10°, usually accompanied by three-dimensional spinal deformity. Scoliosis worsens over time, leading to a series of changes in body shape, such as unequal shoulder height, deviation of the spine from the midline, and razor back. Excessive spinal curvature may also lead to other complications, such as neck, shoulder and lower back pain, paralysis, and cardiovascular and respiratory dysfunction, which may ultimately lead to a higher risk of death. Currently, surgery remains the only effective way to correct severe spinal curvature.

[0003] In the early stages of scoliosis, the degree of spinal curvature is very small and there are no obvious clinical manifestations. The key to preventing and treating scoliosis is early detection, early diagnosis, and early treatment. Screening methods for early scoliosis include flexion tests, scoliometers, and moiré imaging, with suspected patients finally diagnosed through X-rays. As a typical static identification method, individuals usually need to undergo spinal health assessments in specific locations and postures, and the process relies too much on the doctor's subjectivity. Years of practice have shown that the test sensitivity of these traditional static identification methods is only 71.1%, and there are often many missed detections and false detections. In addition, these traditional static identification methods achieve the identification of scoliosis through a single assessment, ignoring the dynamic evolution of the spine as the disease progresses. The continuity of spinal monitoring is poor, and it is difficult to achieve health monitoring of patients with spinal deformities at different stages.

[0004] In summary, the existing technology has the problems of low screening sensitivity, poor monitoring continuity and low intelligence. Summary of the Invention

[0005] The present invention provides an artificial intelligence-assisted spinal health monitoring system to solve the technical problems of low screening sensitivity, poor monitoring continuity and low intelligence level in the existing technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: An artificial intelligence-assisted spinal health monitoring system includes: a spinal health monitoring suit module, an artificial intelligence module, and a cloud center management module; wherein, The spinal health monitoring suit module is used to collect the three-dimensional spinal motion signals when the subject performs different spinal motion patterns, and transmit the collected three-dimensional spinal motion signals to the artificial intelligence module and the cloud center management module; The artificial intelligence module is used to analyze the three-dimensional spinal motion signal based on a deep learning algorithm to determine the health status of the subject and transmit the judgment result to the cloud center management module; The cloud center management module is used to store the three-dimensional spinal motion signals collected by the spinal health monitoring suit module and the health status judgment results of the subject obtained by the artificial intelligence module; and generate the health monitoring data of the subject.

[0007] Furthermore, the spinal health monitoring clothing module includes a tights, a flexible vector sensor and a signal management unit; wherein, The flexible vector sensor is embedded in the bodysuit and electrically connected to the signal management unit; When collecting the subject's three-dimensional spinal motion signal, the tights are worn on the subject. After the subject puts on the tights, the flexible vector sensor is located on the subject's specific body part, which is used to record the deformation amplitude and direction of the specific body part when the subject performs different spinal motion patterns, so as to generate the subject's three-dimensional spinal motion signal when the subject performs different spinal motion patterns, and transmit the generated three-dimensional spinal motion signal to the signal management unit, and then transmit it to the artificial intelligence module and the cloud center management module by the signal management unit.

[0008] Furthermore, the signal management unit includes a single chip control module, a transmission module and a power control module; wherein, The power control module is used to supply power to the single chip control module and the transmission module; The single-chip microcomputer control module is electrically connected to the flexible vector sensor and the transmission module respectively; the single-chip microcomputer control module is used to realize real-time acquisition of multi-channel signals through the flexible vector sensor; the transmission module is used to transmit the three-dimensional motion signal of the spine to the artificial intelligence module and the cloud center management module by wireless transmission.

[0009] Furthermore, the transmission module is a Bluetooth transmission module.

[0010] Furthermore, the spinal movement pattern is any one or more combinations of spinal flexion, extension, left flexion, right flexion, left rotation, right rotation, flexion combined with left flexion, flexion combined with right flexion, extension combined with left flexion, extension combined with right flexion, and rotational movement.

[0011] Furthermore, the specific body part is any one or a combination of the cervical vertebrae, thoracic vertebrae, lumbar vertebrae, sacral vertebrae, coccyx, lower edge of the sternum, the intersection of the left costal margin and the mid-axillary line, and the intersection of the right costal margin and the mid-axillary line.

[0012] Furthermore, the artificial intelligence module includes a prediction algorithm module and a neural network model; wherein, The algorithm module is expected to be used to preprocess the three-dimensional motion signal of the spine; the preprocessed three-dimensional motion signal of the spine is then input into the neural network model, and the neural network model determines the health status of the subject.

[0013] Furthermore, the neural network model is composed of multiple convolutional neural networks.

[0014] Furthermore, the cloud center management module includes a cloud server, a cloud storage and a cloud computing machine; wherein, The cloud storage is used to store the three-dimensional spinal motion signals collected by the spinal health monitoring suit module and the health status judgment results of the subject obtained by the artificial intelligence module; The cloud computing machine is used to generate health monitoring data of the subjects; The cloud server is used to provide external service connections for users to remotely log in to the cloud center management module; after the user logs in to the cloud center management module, he or she can remotely view the corresponding health monitoring data of the subject.

[0015] Furthermore, the health monitoring data includes the subject's corresponding peripheral data and periodic health reports.

[0016] The beneficial effects brought about by the technical solution provided by the present invention include at least: 1. The present invention monitors the amplitude and direction of body surface deformation through flexible force vector sensors, thereby capturing the three-dimensional movement of the spine, developing a strategy for assessing spinal health through spinal movement symmetry, and improving the objectivity, accuracy, and continuity of the spinal deformity screening and treatment process.

[0017] 2. The present invention improves the intelligence of the spinal health monitoring process by combining spinal health monitoring services with artificial intelligence and cloud computing. It has broad application prospects in the early screening, progression monitoring and auxiliary treatment of congenital, idiopathic, neurological, muscular, tumorous, traumatic and degenerative spinal deformities. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 is a structural diagram of an artificial intelligence-assisted spinal health monitoring system provided by an embodiment of the present invention; Figure 2This is a workflow diagram of an artificial intelligence-assisted spinal health monitoring system provided by an embodiment of the present invention; Figure 3 is a structural diagram of a spinal health monitoring suit module provided by an embodiment of the present invention; Figure 4 This is a physical diagram of a spinal health monitoring clothing module provided by an embodiment of the present invention; Figure 5 is a schematic structural diagram of a flexible force vector sensor provided by an embodiment of the present invention; Figure 6 is a physical diagram of a flexible force vector sensor provided by an embodiment of the present invention; Figure 7 is a schematic diagram of a signal management unit provided by an embodiment of the present invention; Figure 8 3D motion signal diagrams of the human spine provided by an embodiment of the present invention; (a) is a 3D motion signal of the spine of a healthy person; (b) is a 3D motion signal of the spine of a patient with mild scoliosis; (c) is a 3D motion signal of the spine of a patient with moderate scoliosis; and (d) is a 3D motion signal of the spine of a patient with severe scoliosis. Figure 9 : The neural network model and confusion matrix diagram provided by the embodiment of the present invention; wherein (a) is a schematic diagram of the neural network model; (b) is a binary classification confusion matrix for scoliosis; (c) is a multi-classification confusion matrix; Figure 10 This is a statistical chart of the accuracy of scoliosis type recognition by the system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0020] To make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0021] First, it should be noted that in the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as an "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "exemplarily" is intended to present concepts in a concrete manner. In addition, in the embodiments of the present invention, the meaning of "and / or" can be both or either of the two.

[0022] This embodiment provides an artificial intelligence-assisted spinal health monitoring system. Figure 1 As shown, it includes: spinal health monitoring suit module, artificial intelligence module and cloud center management module.

[0023] The spinal health monitoring suit module is used to collect the three-dimensional spinal motion signals when the subject performs different spinal motion patterns, and transmit the collected three-dimensional spinal motion signals to the artificial intelligence module and the cloud center management module; The artificial intelligence module is used to analyze the three-dimensional spinal motion signal based on a deep learning algorithm to determine the health status of the subject and transmit the judgment result to the cloud center management module; The cloud center management module is used to store the three-dimensional spinal motion signals collected by the spinal health monitoring suit module and the health status judgment results of the subjects obtained by the artificial intelligence module; and to analyze and present them, and generate corresponding data peripheral and periodic reports for relevant personnel to review, thereby realizing spinal health management.

[0024] Specifically, in this embodiment, Figure 3 and Figure 4 As shown, the spinal health monitoring suit module consists of a tight-fitting garment, a flexible force vector sensor, and a signal management unit.

[0025] Tights come in different models to meet the needs of people with different body mass indexes.

[0026] Flexible force vector sensors are embedded in the bodysuit to record the deformation amplitude and direction of specific body parts under different spinal motion modes. Spinal motion modes include spinal flexion, extension, left lateral flexion, right lateral flexion, left rotation, right rotation, a combination of flexion and left lateral flexion, a combination of flexion and right lateral flexion, a combination of extension and left lateral flexion, a combination of extension and right lateral flexion, and rotation, or a combination of two or more of the following: cervical vertebrae, thoracic vertebrae, lumbar vertebrae, sacral vertebrae, coccyx, lower sternum, the intersection of the left costal margin and the mid-axillary line, and the intersection of the right costal margin and the mid-axillary line. When the flexible strain sensors are placed at the lower sternum and the twelfth thoracic vertebra, the movement of the spine along the sagittal plane can be monitored. When the flexible force vector sensors are placed at the intersection of the left and right costal margins and the mid-axillary line, the movement of the spine along the coronal and transverse planes can be monitored. When the spine performs flexion, extension, left flexion, right flexion, left rotation, right rotation, flexion and left flexion combined, flexion and right flexion combined, extension and left flexion combined, extension and right flexion combined, rotation, or a combination of two or more movements, mechanical sensors at different positions will generate response signals, which together describe the three-dimensional movement of the spine.

[0027] Among them, it should be noted that spinal deformity can reduce spinal flexibility and mobility and cause changes in body surface morphology. Assessing spinal conditions by capturing the three-dimensional movement of the spine will greatly improve the objectivity, continuity, and comprehensiveness of spinal health monitoring. Compared with traditional cameras and inertial measurement units, flexible mechanical sensors are attached to the surface of the body and effectively perceive the three-dimensional movement of the spine by detecting changes in body surface morphology. They are not restricted by space and are not affected by electromagnetic interference, and have great potential in spinal health monitoring applications. In the context of the Internet of Things, the development of intelligent spinal health monitoring methods through the deep cross-integration of multiple disciplines such as materials, electronics, computers, and medicine will greatly promote the screening, diagnosis, and treatment of spinal deformities.

[0028] like Figure 5 and Figure 6 As shown, the flexible force vector sensor comprises, from top to bottom, an upper packaging layer, an upper strain-sensitive layer, a spacer layer, a lower strain-sensitive layer, and a lower packaging layer. The upper packaging layer, spacer layer, and lower packaging layer are circular with a diameter of 40 mm, while the upper and lower strain-sensitive layers are strip-shaped, 52 mm long and 5 mm wide. The mechanical properties of the upper packaging layer, spacer layer, and lower packaging layer are isotropic, while the electromechanical properties of the upper strain-sensitive layer and the lower strain-sensitive layer are anisotropic. The upper and lower strain-sensitive layers are orthogonally stacked. The flexible force vector sensor responds to applied tensile strains in a range of 0-100% and in a range of 0-90° to the loading direction. When different tensile strains are applied in different directions, the two response signals continuously change, and the strength of the two response signals together reflects the magnitude and direction of the applied strain.

[0029] Signal management unit such as Figure 7 As shown, it includes a single-chip control module, a Bluetooth transmission module and a power control module, etc., which can realize real-time acquisition and wireless transmission of multi-channel signals.

[0030] By integrating different units into the tights, the efficiency of spinal health assessment is greatly improved, meeting the requirements for high efficiency and high durability in the screening and treatment of spinal deformities.

[0031] The artificial intelligence module includes a prediction algorithm module and a neural network model. The pre-calculation module first processes the three-dimensional spinal motion signal, including filtering for noise reduction, fast Fourier transform analysis of the spectrum, and wavelet transform extraction of time-frequency features. This is then further trained using a neural network model. The neural network model, composed of multiple convolutional neural networks, takes the three-dimensional spinal motion signal collected by the spinal health monitoring suit module as input data and feeds it into the neural network model already constructed by the artificial intelligence module to generate output data, thereby predicting spinal health.

[0032] Specifically, the neural network model GraphScoDetect of this embodiment is as follows Figure 9 As shown in (a) of Figure 1, GraphScoDetect is a multi-stage deep learning-based scoliosis screening framework consisting of two core stages: pre-training and formal training. The pre-training stage focuses on systematically training the encoder. The encoder receives input signals from healthy individuals and patients. These signals are first converted into numerical code representations via an embedding layer. Subsequently, the embeddings for each channel are constructed as nodes in a graph neural network (GNN), forming a complete graph structure consisting of nodes and edges. These structural parameters are initially randomly initialized and converted to fixed network parameters after multiple network training iterations. The constructed graph structure is used to perform convolution operations on the embeddings to extract asymmetric features representing motion signals. In this process, GraphScoDetect forces the encoding distances of adjacent signal segments of symmetrical sensors in healthy subjects to converge while forcing the encoding distances of signal segments in patients to diverge, thereby enhancing the GNN's ability to represent motion signal asymmetry. To account for inter-individual signal variability, the encoder is trained using a cross-individual self-supervised learning strategy. Specifically, the encoder simultaneously encodes and compares multiple data samples from subjects A and B. These asymmetric encoded representations are then fused to generate a signal-level representation. This further reduces the encoding distances between multiple data samples from the same subject, while significantly widening the distances between samples from different subjects. As a result, the encoder is able to effectively capture the individual characteristics of each subject.

[0033] During the formal training phase, GraphScoDetect jointly trains the encoder and classifier. The classifier consists of a long short-term memory network (LSTM) and a multi-layer perceptron (MLP). This design not only improves the encoder's ability to distinguish the asymmetric movement patterns characteristic of scoliosis, but also synergistically enhances the diagnostic accuracy of the entire framework by integrating the time series processing capabilities of the LSTM and the pattern recognition capabilities of the MLP, thereby promoting the further development of this method in the field of scoliosis screening.

[0034] In this embodiment, 100 samples of 300 motion signals are randomly selected to train the model. First, the samples are randomly divided into two categories. Figure 9 (b) shows the confusion matrix between the predicted and true values for binary classification of the sample motion signal. The accuracy reached 97.5%, demonstrating that the model can effectively distinguish between healthy individuals and scoliosis patients. The samples were further randomly divided into multiple categories: when the Cobb angle was less than 10°, the patient was classified as healthy, and each increase of 15° created a new category. When the Cobb angle exceeded 45°, the patient was classified as severe scoliosis. Figure 9 Figure (c) shows the confusion matrix between the predicted and true values for the multi-classification of the sample motion signals. The accuracy of the scoliosis multi-classification reached 95%, demonstrating that the model can effectively distinguish patients with different degrees of scoliosis. Therefore, the network can effectively identify scoliosis by analyzing the degree of asymmetry in the signals collected from symmetrical parts of the body during symmetrical movements. As the degree of scoliosis increases over time, the degree of asymmetry in the signals collected from symmetrical parts of the body during symmetrical movements increases, making it effective for monitoring scoliosis progression.

[0035] The cloud center management module includes cloud servers, cloud storage, and cloud computing machines. The cloud server provides external service connections. After logging into the cloud management center, users can remotely log in to view their corresponding data and periodic reports. Doctors can then provide remote diagnosis and treatment advice based on these data and periodic reports.

[0036] Among them, peripheral data processing and periodic report generation primarily rely on the data integration and intelligent analysis technologies implemented in the cloud center management module. Specifically, the cloud storage system completes the collection, integration, and structured storage of multi-source data (such as monitoring data and diagnostic records), effectively eliminating redundant information and building a standardized database. The cloud computing module dynamically analyzes data based on preset rules and machine learning models, accurately identifying abnormal indicators and predicting risk trends. It also combines periodic data aggregation (such as weekly / monthly statistics) to generate quantitative assessment results such as the frequency of fluctuations in core indicators and compliance. Ultimately, data summaries, trend comparisons, and AI recommendations are integrated through standardized templates. After permission review, standardized reports are generated that include visual charts (such as health trend curves) and personalized diagnosis and treatment recommendations. At the same time, encrypted storage and version management mechanisms are used to ensure data security and report traceability.

[0037] Furthermore, it should be noted that the principle of spinal health monitoring is to assess spinal function by evaluating the magnitude and direction of surface deformation during spinal movement, as well as the consistency of the magnitude and direction of surface deformation on both sides of the spine under symmetrical spinal movement patterns. Based on this, this embodiment designs a scoliosis screening assessment action for the application scenario of scoliosis screening, using spinal health monitoring clothing to achieve early screening and disease monitoring of scoliosis. A perfect human body exhibits complete bilateral symmetry along the sagittal plane. When the human body performs symmetrical movements to the left and right along the sagittal plane, the corresponding muscle movements on both sides of the human body also exhibit complete symmetry, thus also leading to symmetry in the magnitude and direction of surface deformation. Three-dimensional spinal deformity can cause severe asymmetry in the human body and induce muscle movement disorders, which inevitably lead to differences in surface movement morphology, which can be captured by sensors. After acquiring three-dimensional spinal motion information, the strain vector sensing mechanical sensor analyzes the degree of asymmetry of characteristic signals such as the magnitude and direction of surface skin deformation collected under symmetrical movements, potentially enabling assessment of spinal function and determining whether the spine has deformities and lesions. The human spine is a flexible and dynamic joint composed of 26 vertebrae. It can perform complex movements along the sagittal, coronal, and transverse planes, including flexion and extension, lateral flexion, rotation, and circumduction. The sensor placement needs to effectively reflect multi-dimensional movement in the sagittal, coronal, and transverse planes. Flexible mechanical sensors were placed symmetrically at two locations: the lower sternum and the 12th thoracic vertebra, and at the intersection of the left and right costal margins and the mid-axillary line. These locations are where the spine has the greatest range of motion and can fully reflect its three-dimensional motion. Because the lower sternum and the 12th thoracic vertebra exhibit relatively simple motion patterns, flexible strain sensors were placed at these locations to monitor the magnitude of surface deformation during movement. However, the left and right sides exhibit relatively complex motion patterns, so flexible force vector sensors were placed there to monitor the magnitude and direction of surface deformation. During movement, the three-dimensional motion of the spine is captured using six monitoring signals from four sensors.

[0038] Furthermore, this embodiment designs motions for human spinal health monitoring. The human spine is complex in structure. To better correlate spinal motion with the body's sagittal, coronal, and transverse planes, three sets of symmetrical motions are designed: spinal flexion and extension, left and right flexion, and left and right rotation. Spinal flexion and extension primarily reflect the body's symmetry along the sagittal plane, while left and right flexion primarily reflect the body's symmetry along the coronal plane, and left and right rotation further reflects the body's symmetry along the transverse plane. Theoretically, a normal human body is perfectly symmetrical along the coronal plane. When the two sensors are worn on the designed body parts, the magnitude and direction of skin deformation caused by changes in body surface morphology under symmetrical motions are similar. In contrast, patients with scoliosis experience severe body asymmetry due to spinal deformity. The magnitude and direction of skin deformation caused by changes in body surface morphology under symmetrical motions are different. Furthermore, the greater the angle of scoliosis, the more asymmetric the characteristic motion signal. By measuring the degree of asymmetry of the characteristic motion signal, it is possible to determine whether the patient has scoliosis and the degree of scoliosis.

[0039] The process of implementing health monitoring using the above-mentioned spinal health monitoring system is as follows: Figure 2 As shown, including: 1. The spinal health monitoring suit module monitors the deformation amplitude and direction of specific body parts under different spinal movement modes, acquires the three-dimensional motion signal of the spine and transmits it to the artificial intelligence module.

[0040] 2. The artificial intelligence module analyzes and calculates the collected three-dimensional motion signals of the spine in real time to obtain the corresponding calculation results.

[0041] 3. The cloud center management module stores collected data and calculation results, analyzes and presents them, and generates corresponding data peripheral and periodic reports, thereby achieving spinal health management.

[0042] The three-dimensional motion signal of the spine obtained by detection is as follows Figure 8 As shown in the figure, the test subjects wore spinal health monitoring clothing and, under the guidance of a doctor, performed three sets of symmetrical movements, namely flexion and extension, left and right bending, and left and right rotation, in sequence, trying to reach the maximum range of motion in each set. Figure 8(a) in the figure shows the real-time motion signals collected from a healthy individual's spine. Experimental results show that flexion and extension motion signals are more pronounced. This is because healthy individuals have good spinal flexibility and are capable of large-scale flexion and extension movements. When a healthy individual performs left and right bending movements, the tensile deformation of the upper and lower strain-sensitive layers of the strain vector sensing mechanosensor is consistent, resulting in consistent response signals from the upper and lower strain-sensitive layers. Furthermore, the motion signal intensities measured for left and right bending movements are approximately the same. Furthermore, when a healthy individual rotates left, the skin deformation amplitude and direction change. Both the upper sensing layer of the right strain vector sensing mechanosensor and the lower sensing layer of the left strain vector sensing mechanosensor generate response signals, and there is a certain difference in the intensities of the two characteristic signals. When a healthy individual rotates right, the amplitudes of the characteristic motion signals from the lower sensing layer of the right strain vector sensing mechanosensor and the lower sensing layer of the left strain vector sensing mechanosensor, as well as the upper sensing layer of the left strain vector sensing mechanosensor and the upper sensing layer of the right strain vector sensing mechanosensor, are consistent. The characteristic motion signal intensities measured for left and right rotations are highly consistent. The characteristic motion signals of scoliosis patients were further collected clinically, such as Figure 8 As shown in (b), scoliosis can significantly reduce spinal flexibility, so the amplitude of the patient's flexion and extension movement signals will decrease, and the patient's left and right bending, left rotation and right rotation characteristic movement signals will be severely asymmetric. Figure 8 As shown in (c) and (d) in the figure, as the degree of scoliosis in clinical patients increases, the asymmetry of the motion signals becomes more obvious.

[0043] After experimental verification, the accuracy of scoliosis type identification using the spine health monitoring system of this embodiment is as follows: Figure 10 As shown, it can be seen that this embodiment can accurately identify the position of scoliosis by analyzing the three-dimensional motion signal of the spine through an artificial neural network. Among them, the accuracy rate of identifying thoracic curvature reaches 100%, the accuracy rate of identifying thoracolumbar curvature reaches 86.67%, and the accuracy rate of identifying lumbar curvature reaches 93.33%.

[0044] In summary, this embodiment provides an artificial intelligence-assisted spinal health monitoring system. Through the deep cross-integration of materials, electronics, computers and medicine, it innovates the screening, diagnosis and treatment technology of spinal deformities. It can provide customized health assessment and management plans for the health monitoring needs of different spinal deformities. Through the evaluation of spinal kinematics and its symmetry, it can be widely used for early screening, progression monitoring and assisted rehabilitation of congenital, idiopathic, neurological, muscular, tumorous, traumatic and degenerative spinal deformities.

[0045] Furthermore, it should be noted that the present invention may be provided as a method, apparatus, or computer program product. Therefore, embodiments of the present invention may take the form of fully or partially hardware embodiments, fully or partially software embodiments, or embodiments combining software and hardware. Furthermore, when implemented using software, embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code. The computer program product comprises one or more computer instructions or computer programs. When loaded or executed on a computer, the processes or functions described in accordance with the embodiments of the present invention are fully or partially performed. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer instructions may be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired communication (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium may be any computer-accessible medium or a data storage device, such as a server or data center, containing a collection of one or more computer-readable media. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium. The semiconductor medium may be a solid-state drive.

[0046] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the process in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0047] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, so that a series of operation steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for implementing the process in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0048] It should also be noted that, as used herein, the terms "comprise," "include," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or terminal device comprising a set of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, article, or terminal device. Without further limitation, the phrase "comprises a..." does not preclude the presence of additional identical elements in the process, method, article, or terminal device comprising the elements. Furthermore, the term "and / or" is merely a description of an association between associated objects, indicating that three possible relationships can exist. For example, "A and / or B" can mean: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. Furthermore, the character " / " in this document generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship, which should be understood with reference to the context. "At least one" refers to one or more, and "more" refers to two or more. "At least one of the following" or similar expressions refers to any combination of those items, including any combination of single or plural items. For example, "at least one of a, b, or c" can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0049] In addition, it can be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0050] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0051] In the several embodiments provided herein, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of functional modules / units is merely a logical functional division. In actual implementation, other division methods may be used, such as multiple units or components being combined or integrated into another device, or some features being ignored or not implemented. Furthermore, the coupling or direct coupling or communication connection shown or discussed between each other may be through some interface, indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms. Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, i.e., they may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of the present embodiment according to actual needs. In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit.

[0052] If the method is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or the portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical disks.

[0053] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention. It should be noted that, although preferred embodiments of the present invention have been described, those skilled in the art, once understanding the basic inventive concepts of the present invention, may make various improvements and modifications without departing from the principles of the present invention. Such improvements and modifications should also be considered within the scope of protection of the present invention. Therefore, the appended claims are intended to be interpreted as covering the preferred embodiments and all variations and modifications that fall within the scope of the embodiments of the present invention.

Claims

1. An artificial intelligence-assisted spinal health monitoring system, characterized in that: include: Spinal health monitoring module, artificial intelligence module and cloud center management module; among them, The spinal health monitoring suit module is used to collect the three-dimensional spinal motion signals when the subject performs different spinal motion patterns, and transmit the collected three-dimensional spinal motion signals to the artificial intelligence module and the cloud center management module; The artificial intelligence module is used to analyze the three-dimensional spinal motion signal based on a deep learning algorithm to determine the health status of the subject and transmit the judgment result to the cloud center management module; The cloud center management module is used to store the three-dimensional spinal motion signals collected by the spinal health monitoring suit module and the health status judgment results of the subject obtained by the artificial intelligence module; and generate the health monitoring data of the subject.

2. The artificial intelligence-assisted spinal health monitoring system according to claim 1, characterized in that: The spinal health monitoring clothing module includes a tights, a flexible vector sensor and a signal management unit; wherein, The flexible vector sensor is embedded in the bodysuit and electrically connected to the signal management unit; When collecting the subject's three-dimensional spinal motion signal, the tights are worn on the subject. After the subject puts on the tights, the flexible vector sensor is located on the subject's specific body part, which is used to record the deformation amplitude and direction of the specific body part when the subject performs different spinal motion patterns, so as to generate the subject's three-dimensional spinal motion signal when the subject performs different spinal motion patterns, and transmit the generated three-dimensional spinal motion signal to the signal management unit, and then transmit it to the artificial intelligence module and the cloud center management module by the signal management unit.

3. The artificial intelligence-assisted spinal health monitoring system according to claim 2, wherein: The signal management unit includes a single chip control module, a transmission module and a power control module; wherein, The power control module is used to supply power to the single chip control module and the transmission module; The single-chip microcomputer control module is electrically connected to the flexible vector sensor and the transmission module respectively; the single-chip microcomputer control module is used to realize real-time acquisition of multi-channel signals through the flexible vector sensor; the transmission module is used to transmit the three-dimensional motion signal of the spine to the artificial intelligence module and the cloud center management module by wireless transmission.

4. The artificial intelligence-assisted spinal health monitoring system according to claim 3, wherein: The transmission module is a Bluetooth transmission module.

5. The artificial intelligence-assisted spinal health monitoring system according to claim 1, wherein: The spinal movement pattern is any one or more combinations of spinal flexion, extension, left flexion, right flexion, left rotation, right rotation, flexion combined with left flexion, flexion combined with right flexion, extension combined with left flexion, extension combined with right flexion, and rotation.

6. The artificial intelligence-assisted spinal health monitoring system according to claim 2, wherein: The specific body part is any one or a combination of the cervical vertebrae, thoracic vertebrae, lumbar vertebrae, sacral vertebrae, coccyx, lower edge of the sternum, the intersection of the left costal margin and the mid-axillary line, and the intersection of the right costal margin and the mid-axillary line.

7. The artificial intelligence-assisted spinal health monitoring system according to claim 1, wherein: The artificial intelligence module includes a prediction algorithm module and a neural network model; wherein, The algorithm module is expected to be used to preprocess the three-dimensional motion signal of the spine; the preprocessed three-dimensional motion signal of the spine is then input into the neural network model, and the neural network model determines the health status of the subject.

8. The artificial intelligence-assisted spinal health monitoring system according to claim 7, wherein: The neural network model consists of multiple convolutional neural networks.

9. The artificial intelligence-assisted spinal health monitoring system according to claim 1, wherein: The cloud center management module includes a cloud server, a cloud storage and a cloud computing machine; wherein, The cloud storage is used to store the three-dimensional spinal motion signals collected by the spinal health monitoring suit module and the health status judgment results of the subject obtained by the artificial intelligence module; The cloud computing machine is used to generate health monitoring data of the subjects; The cloud server is used to provide external service connections for users to remotely log in to the cloud center management module; after the user logs in to the cloud center management module, he or she can remotely view the corresponding health monitoring data of the subject.

10. The artificial intelligence-assisted spinal health monitoring system according to claim 9, wherein: The health monitoring data includes the subject's corresponding peripheral data and periodic health reports.

Images