Artificial intelligence-based osteoporosis risk assessment method and system

Abstract

The invention discloses an artificial intelligence-based osteoporosis risk assessment method and system. The method comprises the steps of receiving feedback information of a first user for an online osteoporosis risk questionnaire; according to the feedback information, determining a first risk score that the first user suffers from osteoporosis; screening a second user with a potential osteoporosis risk according to the first risk score; acquiring historical diagnosis and treatment information of the second user in each networked hospital, and searching diagnosis and treatment data related to osteoporosis diagnosis; and if the diagnosis and treatment data is found, based on the diagnosis and treatment data, determining a second risk score that the second user suffers from osteoporosis by using a pre-trained osteoporosis risk assessment model based on artificial intelligence, and sending the second risk score to the second user terminal. By utilizing the embodiment of the invention, the osteoporosis risk can be evaluated in real time in combination with the artificial intelligence technology, the screening efficiency of the osteoporosis is improved, the fracture risk is reduced, and the management and intervention effects of the osteoporosis are improved on the public health level.

Description

Technical Field

[0001] The present invention belongs to the field of artificial intelligence technology, and in particular to an osteoporosis risk assessment method and system based on artificial intelligence. Background Art

[0002] Osteoporosis is a common metabolic bone disease characterized by decreased bone density and disrupted bone microarchitecture, leading to increased bone fragility and fracture risk. Particularly in the elderly, osteoporosis-induced fractures not only impact patients' quality of life but also increase their healthcare burden. Therefore, early identification and assessment of osteoporosis risk are crucial. Summary of the Invention

[0003] The purpose of the present invention is to provide an artificial intelligence-based osteoporosis risk assessment method and system to address the deficiencies in the existing technology. It can combine artificial intelligence technology to assess osteoporosis risk in real time, help improve the screening efficiency of osteoporosis, reduce the risk of fractures, and improve the management and intervention effects of osteoporosis at the public health level.

[0004] One embodiment of the present application provides an artificial intelligence-based osteoporosis risk assessment method, the method comprising:

[0005] receiving feedback from the first user on the online osteoporosis risk questionnaire;

[0006] determining, based on the feedback information, a first risk score for the first user suffering from osteoporosis;

[0007] screening a second user with a potential risk of osteoporosis from the first users according to the first risk score;

[0008] Obtaining historical medical information of the second user at each networked hospital, and searching for medical data related to osteoporosis diagnosis from the historical medical information;

[0009] If the diagnosis and treatment data is found, based on the diagnosis and treatment data, a pre-trained artificial intelligence-based osteoporosis risk assessment model is used to determine a second risk score for the second user suffering from osteoporosis and send it to the second user terminal.

[0010] Optionally, the method further includes:

[0011] If the diagnosis and treatment data is found, the first risk score is sent to the first user terminal excluding the second user;

[0012] If no diagnosis and treatment data is found, the first risk score is sent to all first user terminals.

[0013] Optionally, according to the gender and age information of the first user, a corresponding pre-designed osteoporosis risk questionnaire is pushed to the first user;

[0014] The step of screening a second user with a potential risk of osteoporosis from the first user according to the first risk score includes:

[0015] Determining a risk threshold corresponding to the gender type and age group according to the gender type and age group of the first user;

[0016] If the first risk score of the first user is higher than the corresponding risk threshold, the first user is determined to be a second user with a potential risk of osteoporosis.

[0017] Optionally, based on the diagnosis and treatment data, using a pre-trained artificial intelligence-based osteoporosis risk assessment model to determine a second risk score for osteoporosis for the second user and sending the score to the second user terminal includes:

[0018] classifying the diagnosis and treatment data into laboratory data and imaging data;

[0019] inputting the test data into a pre-trained first osteoporosis risk assessment model based on artificial intelligence, and outputting a second test risk sub-score indicating that the second user suffers from osteoporosis;

[0020] Inputting the image data into a pre-trained second osteoporosis risk assessment model based on artificial intelligence, and outputting a second image risk sub-score indicating that the second user suffers from osteoporosis;

[0021] A second risk score for osteoporosis for the second user is calculated based on the second laboratory risk sub-score and the second imaging risk sub-score and sent to the second user terminal.

[0022] Another embodiment of the present application provides an artificial intelligence-based osteoporosis risk assessment system, the system comprising:

[0023] A receiving module, configured to receive feedback information from a first user on an online osteoporosis risk questionnaire;

[0024] a first determining module, configured to determine a first risk score for the first user suffering from osteoporosis based on the feedback information;

[0025] a screening module, configured to screen a second user with a potential risk of osteoporosis from among the first users based on the first risk score;

[0026] a search module, configured to obtain historical diagnosis and treatment information of the second user at each networked hospital, and search for diagnosis and treatment data related to osteoporosis diagnosis from the historical diagnosis and treatment information;

[0027] The second determination module is used to determine the second risk score of the second user suffering from osteoporosis based on the diagnosis and treatment data and send it to the second user terminal by using a pre-trained artificial intelligence-based osteoporosis risk assessment model if the diagnosis and treatment data is found.

[0028] Yet another embodiment of the present application provides a storage medium, wherein the storage medium stores a computer program, wherein the computer program is configured to execute any of the above methods when run.

[0029] Yet another embodiment of the present application provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute any of the above methods.

[0030] Compared with the existing technology, the present invention provides an artificial intelligence-based osteoporosis risk assessment method, which receives feedback information from a first user on an online osteoporosis risk questionnaire; determines a first risk score for the first user suffering from osteoporosis based on the feedback information; screens a second user with potential osteoporosis risk from the first user based on the first risk score; obtains the second user's historical medical information in each networked hospital, and searches for medical data related to osteoporosis diagnosis from the historical medical information; if medical data is found, based on the medical data, uses a pre-trained artificial intelligence-based osteoporosis risk assessment model to determine the second risk score for the second user suffering from osteoporosis and sends it to the second user terminal, thereby being able to combine artificial intelligence technology to assess osteoporosis risk in real time, which helps to improve the screening efficiency of osteoporosis, reduce the risk of fractures, and improve the management and intervention effects of osteoporosis at the public health level. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 A hardware structure block diagram of a computer terminal for an artificial intelligence-based osteoporosis risk assessment method provided in an embodiment of the present invention;

[0032] Figure 2 A schematic diagram of a flow chart of an artificial intelligence-based osteoporosis risk assessment method provided in an embodiment of the present invention;

[0033] Figure 3 A schematic structural diagram of an artificial intelligence-based osteoporosis risk assessment system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and are not to be construed as limiting the present invention.

[0035] The embodiment of the present invention first provides an osteoporosis risk assessment method based on artificial intelligence, which can be applied to electronic devices such as computer terminals, specifically ordinary computers.

[0036] The following describes it in detail by taking running on a computer terminal as an example. Figure 1 The hardware structure block diagram of a computer terminal for an artificial intelligence-based osteoporosis risk assessment method provided in an embodiment of the present invention. Figure 1 As shown, the computer terminal may include one or more ( Figure 1 Only one is shown) a processor 102 (the processor 102 may include but is not limited to a microprocessor MCU or a programmable logic device FPGA and other processing devices) and a memory 104 for storing data. Optionally, the computer terminal may also include a transmission device 106 for communication functions and an input and output device 108. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above-mentioned computer terminal. For example, the computer terminal may also include Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0037] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / modules corresponding to the artificial intelligence-based osteoporosis risk assessment method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, implementing the above-mentioned method. The memory 104 may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely located relative to the processor 102, and these remote memories may be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0038] The transmission device 106 is used to receive or send data via a network. A specific example of the aforementioned network may include a wireless network provided by a communications provider of a computer terminal. In one embodiment, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0039] See also Figure 2 , an embodiment of the present invention provides an osteoporosis risk assessment method based on artificial intelligence, which may include the following steps:

[0040] S201, receiving feedback information from a first user on an online osteoporosis risk questionnaire;

[0041] In modern medicine, early screening and risk assessment for osteoporosis are key measures for preventing fractures and related complications. Receiving feedback from the first user on an online osteoporosis risk questionnaire is the first step in this assessment process. Through this process, the system gathers the user's basic health information, lifestyle, family history, and other potential risk factors. This information not only directly informs preliminary risk scoring but also provides crucial foundational data for subsequent data analysis and model training.

[0042] Specifically, a multi-dimensional questionnaire can be designed, covering physiological indicators, living habits, previous medical history, family medical history, etc., with a total of at least 30 questions. Each question is scored according to the Likert five-point scale to ensure that users can express their situation in a quantitative way when giving feedback; use natural language processing (NLP) technology to dynamically adjust the content of the questionnaire based on user feedback information. For example, based on the user's initial answer (such as age, gender, health status), relevant risk questions are automatically selected to make subsequent questions more targeted, reduce irrelevant questions, and improve the user's filling efficiency; the collected feedback information undergoes data standardization, including missing value filling, outlier detection and normalization conversion, so that subsequent analysis can be carried out under the same standard. Use the Z-score standardization method to convert each item of feedback information into a standard normal distribution value to ensure that information of different dimensions is comparable.

[0043] S202: Determine a first risk score for osteoporosis of the first user based on the feedback information;

[0044] This step converts multi-dimensional health data into a quantitative risk score based on the user's completed questionnaire information, providing a more intuitive assessment of the user's osteoporosis risk. This process primarily involves data processing, feature extraction, and the application of risk scoring algorithms to ensure that noteworthy risk indicators are extracted from complex user feedback.

[0045] Specifically, the risk factor feedback information in the questionnaire can be converted into a multi-faceted score using a preset scoring standard. Risk factors include: age, gender, weight, eating habits, exercise frequency, medical history, family medical history, medication status, environmental factors, etc. A calculation formula for the first risk score can be:

[0046]

[0047] Where R is the osteoporosis risk score of the first user; W_i is the weight of the i-th risk factor, which can be set based on historical data or expert evaluation, and n is the number of risk factors; F_i is the standardized value of the i-th risk factor, which is converted to a standardized value between 0 and 1 according to the preset scoring standard. For example, the user's age and weight are converted to values ​​between 0 and 1, and the user's answers (including options and text answers, etc.) are converted to values ​​between 0 and 1; E(C) is the user's living environment scoring function, which evaluates the impact of the user's environment on bone health based on the questionnaire, such as pollution and urbanization level. One calculation method can be:

[0048]

[0049] Among them, C_positive and C_negative represent the number of positive and negative environmental factors (obtained from the questionnaire), respectively.

[0050] H(A) is a user's health behavior scoring function, based on a questionnaire assessment of the user's health habits such as diet and exercise. One calculation method can be:

[0051]

[0052] Among them, D is the user's diet quality score, E is the exercise score, D_max and E_max are the historical highest scores of diet quality and exercise respectively (obtained from the questionnaire).

[0053] The first risk score formula effectively avoids the influence of a single factor by weighted integration of multiple risk factors, making the score more comprehensive; the introduction of E(C) and H(A) scoring functions makes the risk score not only related to individual characteristics, but also takes into account the influence of environment and health behavior, which is in line with the complexity of actual clinical assessment; through the introduction of E(C) and H(A) functions, the score is not only linearly accumulated, but also introduces a dynamic adjustment mechanism, making the risk assessment of different users in different environments and health habits more accurate and personalized.

[0054] S203: Screening a second user with a potential risk of osteoporosis from among the first users based on the first risk score;

[0055] During the assessment process, the primary risk score is a key metric, reflecting the primary user's osteoporosis risk level. Based on this, analysis of the primary risk score allows for the identification of secondary users with similar risk profiles within the same user group. This is done to more effectively identify and focus on individuals who may require further medical intervention. For example, if the primary user's risk score is significantly higher than average, it may be necessary to identify users with similar profiles within their social network or related user groups to provide potential risk warnings and interventions.

[0056] Specifically, a pre-designed osteoporosis risk questionnaire may be pushed to the first user based on the first user's gender and age information;

[0057] Based on the user's basic information (such as gender and age), the system selects a risk questionnaire relevant to them to ensure relevance and applicability. Osteoporosis risk varies significantly across genders and age groups, so customized questionnaires can improve user engagement and feedback quality.

[0058] Using user profiles from the user management system, a rules engine can be used to determine the user's gender and age group. Machine learning algorithms (such as decision trees or support vector machines) can then analyze the responses to previously validated questionnaires to generate a set of key questions tailored to a specific group. After integrating this information, a personalized questionnaire is then delivered to the first user's device via a push system.

[0059] The risk threshold corresponding to the gender type and age group may be determined based on the gender type and age group of the first user;

[0060] After obtaining the first user's initial risk score, the system automatically filters users from the user database based on a set risk threshold, identifying users with similar risk scores and matching the first user's profile. This creates a group of potentially high-risk users. By comparing the first user's risk score, potentially high-risk users can be quickly identified, providing a basis for subsequent assessment and intervention. Categorizing users with similar high-risk characteristics helps form communities and promote information sharing and support among users.

[0061] If the first risk score of the first user is higher than the corresponding risk threshold, the first user is determined to be a second user with a potential risk of osteoporosis.

[0062] The first user's risk score is compared with the corresponding risk threshold to determine whether they are a risky user requiring special attention. This threshold is usually set based on historical data and clinical research results to ensure scientific and effective results.

[0063] Categorizing users into different risk levels will help medical institutions take stricter monitoring and intervention measures for high-risk groups; through timely risk identification, medical resources can be concentrated on high-risk users, which will help reduce the incidence of complications such as fractures.

[0064] S204, obtaining historical medical information of the second user at each networked hospital, and searching for medical data related to osteoporosis diagnosis from the historical medical information;

[0065] After determining the second user's potential osteoporosis risk, obtaining their historical medical records from various networked hospitals is a key step. This process not only provides a more comprehensive health background but also helps identify symptoms and diagnostic information related to osteoporosis. Through in-depth analysis of historical medical data, possible disease signs can be effectively identified, providing a scientific basis for subsequent risk assessment and intervention measures.

[0066] Specifically, the existing medical and health platform can be used to obtain the second user's historical diagnosis and treatment information in each networked hospital on the medical and health platform, and the second user's historical diagnosis and treatment information can be divided into structured data (such as electronic medical records, laboratory reports) and unstructured data (such as doctors' diagnosis and treatment records, imaging data). Natural language processing (NLP) is used to convert unstructured data into analyzable structured information to enhance the availability of data. It is possible to find out whether the second user has done examinations related to osteoporosis diagnosis. If the corresponding examinations have been done, the examination data are obtained as diagnosis and treatment data. The diagnosis and treatment data related to osteoporosis obtained by analysis, the user's health history, and related imaging data can be integrated to generate a comprehensive risk assessment report. Using data visualization technology, the diagnosis and treatment data can be presented in the form of charts, heat maps, etc., which are convenient for doctors and users to understand.

[0067] S205: If the diagnosis and treatment data is found, based on the diagnosis and treatment data, a pre-trained artificial intelligence-based osteoporosis risk assessment model is used to determine a second risk score for the second user suffering from osteoporosis and send it to the second user terminal.

[0068] In this step, if the system successfully locates the second user's relevant medical data, it will analyze it using a pre-trained AI-based risk assessment model. This process involves inputting the medical data into the model, which, through calculation and inference, generates a second risk score for osteoporosis. This score provides valuable guidance for subsequent health management and interventions.

[0069] Specifically, the diagnosis and treatment data can be classified into laboratory data and imaging data;

[0070] After acquiring the second user's medical data, the system first categorizes the data for targeted analysis. In medical data, laboratory data typically includes blood and biochemical test results, while imaging data includes imaging examination results such as X-rays, CT scans, or MRIs.

[0071] inputting the test data into a pre-trained first osteoporosis risk assessment model based on artificial intelligence, and outputting a second test risk sub-score indicating that the second user suffers from osteoporosis;

[0072] Classified laboratory data is fed into an AI-based assessment model, trained with historical data to identify biomarkers and other relevant factors that influence osteoporosis risk and assign a specific laboratory risk subscore. By analyzing laboratory data using a specialized model, a user's specific osteoporosis risk can be quantitatively assessed, providing a more precise risk stratification. The laboratory risk subscore quantifies the relationship between various biochemical markers and osteoporosis, providing data support for subsequent research.

[0073] Inputting the image data into a pre-trained second osteoporosis risk assessment model based on artificial intelligence, and outputting a second image risk sub-score indicating that the second user suffers from osteoporosis;

[0074] Similarly, the classified imaging data is fed into an AI-based assessment model, which analyzes the imaging results, identifies any possible osteoporosis-related lesions or features, and generates an imaging risk subscore. This specialized model analyzes imaging data, enabling a more nuanced understanding of bone health, adding a crucial dimension to risk assessment. This imaging risk subscore can provide clinicians with more scientific context when making diagnoses, enabling better decision-making.

[0075] A second risk score for osteoporosis for the second user is calculated based on the second laboratory risk sub-score and the second imaging risk sub-score and sent to the second user terminal.

[0076] The final step is to integrate the subscores from the laboratory and imaging data to calculate a comprehensive osteoporosis risk score, which is then sent to the second user's terminal. By integrating data from different sources, the resulting risk score can more comprehensively reflect the user's health status and provide data support for subsequent health management. The final result is sent to the user's terminal, allowing the user to quickly understand their osteoporosis risk and take necessary actions. The second risk score can be calculated by assigning different weights to the laboratory and imaging risk subscores based on a weighted summation method. The weighting can be based on historical data analysis and expert opinion.

[0077] Furthermore, if the diagnosis and treatment data is found, the first risk score may be sent to the first user terminal excluding the second user;

[0078] In this step, the system first confirms whether it has successfully found the second user's medical data. If the data exists, the first user's risk score is sent to all other user terminals related to the second user (that is, excluding the second user). This operation is intended to ensure that potential risk information can be extended to other users, thereby promoting group health awareness.

[0079] If no diagnosis and treatment data is found, the first risk score is sent to all first user terminals.

[0080] During this step, the system considers the possibility that the second user's medical data cannot be found. If the relevant medical information cannot be obtained, the first user's risk score is directly sent to all of the first user's devices. This means that even if the risk assessment cannot be supported by medical data, it is still necessary to ensure the widespread dissemination of information to protect the first user's right to be informed of their health risks.

[0081] The above steps demonstrate the importance and potential value of information sharing in the risk assessment process. This approach not only promotes interaction and connection between users, but also provides a scientific basis for personal health management, continuously promoting the development and application of health technology.

[0082] It can be seen that the feedback information of the first user on the online osteoporosis risk questionnaire is received; based on the feedback information, the first risk score of the first user suffering from osteoporosis is determined; based on the first risk score, a second user with potential osteoporosis risk is screened from the first user; the historical diagnosis and treatment information of the second user in each networked hospital is obtained, and diagnosis and treatment data related to osteoporosis diagnosis are searched from the historical diagnosis and treatment information; if the diagnosis and treatment data is found, based on the diagnosis and treatment data, a pre-trained artificial intelligence-based osteoporosis risk assessment model is used to determine the second risk score of the second user suffering from osteoporosis and send it to the second user terminal, so that the osteoporosis risk can be evaluated in real time by combining artificial intelligence technology, which helps to improve the screening efficiency of osteoporosis, reduce the risk of fractures, and improve the management and intervention effects of osteoporosis at the public health level.

[0083] Another embodiment of the present invention provides an osteoporosis risk assessment system based on artificial intelligence, see Figure 3 , the system may include:

[0084] Receiving module 301, configured to receive feedback information from a first user on an online osteoporosis risk questionnaire;

[0085] A first determining module 302 is configured to determine a first risk score for osteoporosis of the first user based on the feedback information;

[0086] A screening module 303 is configured to screen a second user with a potential risk of osteoporosis from among the first users based on the first risk score;

[0087] Search module 304, configured to obtain historical diagnosis and treatment information of the second user at each networked hospital, and search for diagnosis and treatment data related to osteoporosis diagnosis from the historical diagnosis and treatment information;

[0088] The second determination module 305 is used to determine the second risk score of osteoporosis for the second user based on the diagnosis and treatment data and send it to the second user terminal using a pre-trained artificial intelligence-based osteoporosis risk assessment model if the diagnosis and treatment data is found.

[0089] It can be seen that the feedback information of the first user on the online osteoporosis risk questionnaire is received; based on the feedback information, the first risk score of the first user suffering from osteoporosis is determined; based on the first risk score, a second user with potential osteoporosis risk is screened from the first user; the historical diagnosis and treatment information of the second user in each networked hospital is obtained, and diagnosis and treatment data related to osteoporosis diagnosis are searched from the historical diagnosis and treatment information; if the diagnosis and treatment data is found, based on the diagnosis and treatment data, a pre-trained artificial intelligence-based osteoporosis risk assessment model is used to determine the second risk score of the second user suffering from osteoporosis and send it to the second user terminal, so that the osteoporosis risk can be evaluated in real time by combining artificial intelligence technology, which helps to improve the screening efficiency of osteoporosis, reduce the risk of fractures, and improve the management and intervention effects of osteoporosis at the public health level.

[0090] An embodiment of the present invention further provides a storage medium storing a computer program, wherein the computer program is configured to execute the steps of any one of the above method embodiments when running.

[0091] Specifically, in this embodiment, the above-mentioned storage medium may be configured to store a computer program for performing the following steps:

[0092] S201, receiving feedback information from a first user on an online osteoporosis risk questionnaire;

[0093] S202: Determine a first risk score for osteoporosis of the first user based on the feedback information;

[0094] S203: Screening a second user with a potential risk of osteoporosis from among the first users based on the first risk score;

[0095] S204, obtaining historical medical information of the second user at each networked hospital, and searching for medical data related to osteoporosis diagnosis from the historical medical information;

[0096] S205: If the diagnosis and treatment data is found, based on the diagnosis and treatment data, a pre-trained artificial intelligence-based osteoporosis risk assessment model is used to determine a second risk score for the second user suffering from osteoporosis and send it to the second user terminal.

[0097] It can be seen that the feedback information of the first user on the online osteoporosis risk questionnaire is received; based on the feedback information, the first risk score of the first user suffering from osteoporosis is determined; based on the first risk score, a second user with potential osteoporosis risk is screened from the first user; the historical diagnosis and treatment information of the second user in each networked hospital is obtained, and diagnosis and treatment data related to osteoporosis diagnosis are searched from the historical diagnosis and treatment information; if the diagnosis and treatment data is found, based on the diagnosis and treatment data, a pre-trained artificial intelligence-based osteoporosis risk assessment model is used to determine the second risk score of the second user suffering from osteoporosis and send it to the second user terminal, so that the osteoporosis risk can be evaluated in real time by combining artificial intelligence technology, which helps to improve the screening efficiency of osteoporosis, reduce the risk of fractures, and improve the management and intervention effects of osteoporosis at the public health level.

[0098] An embodiment of the present invention further provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to perform the steps in any one of the above method embodiments.

[0099] Specifically, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0100] Specifically, in this embodiment, the processor may be configured to execute the following steps through a computer program:

[0101] S201, receiving feedback information from a first user on an online osteoporosis risk questionnaire;

[0102] S202: Determine a first risk score for osteoporosis of the first user based on the feedback information;

[0103] S203: Screening a second user with a potential risk of osteoporosis from among the first users based on the first risk score;

[0104] S204, obtaining historical medical information of the second user at each networked hospital, and searching for medical data related to osteoporosis diagnosis from the historical medical information;

[0105] S205: If the diagnosis and treatment data is found, based on the diagnosis and treatment data, a pre-trained artificial intelligence-based osteoporosis risk assessment model is used to determine a second risk score for the second user suffering from osteoporosis and send it to the second user terminal.

[0106] It can be seen that the feedback information of the first user on the online osteoporosis risk questionnaire is received; based on the feedback information, the first risk score of the first user suffering from osteoporosis is determined; based on the first risk score, a second user with potential osteoporosis risk is screened from the first user; the historical diagnosis and treatment information of the second user in each networked hospital is obtained, and diagnosis and treatment data related to osteoporosis diagnosis are searched from the historical diagnosis and treatment information; if the diagnosis and treatment data is found, based on the diagnosis and treatment data, a pre-trained artificial intelligence-based osteoporosis risk assessment model is used to determine the second risk score of the second user suffering from osteoporosis and send it to the second user terminal, so that the osteoporosis risk can be evaluated in real time by combining artificial intelligence technology, which helps to improve the screening efficiency of osteoporosis, reduce the risk of fractures, and improve the management and intervention effects of osteoporosis at the public health level.

[0107] The above describes in detail the structure, features and effects of the present invention based on the embodiments shown in the drawings. The above is only a preferred embodiment of the present invention, but the scope of implementation of the present invention is not limited to what is shown in the drawings. Any changes made in accordance with the concept of the present invention, or modifications to equivalent embodiments with equivalent changes, which do not exceed the spirit covered by the description and drawings, should be within the scope of protection of the present invention.

Claims

1. An osteoporosis risk assessment method based on artificial intelligence, characterized in that: The method comprises: receiving feedback from the first user on the online osteoporosis risk questionnaire; determining, based on the feedback information, a first risk score for the first user suffering from osteoporosis; screening a second user with a potential risk of osteoporosis from the first users according to the first risk score; Obtaining historical medical information of the second user at each networked hospital, and searching for medical data related to osteoporosis diagnosis from the historical medical information; If the diagnosis and treatment data is found, based on the diagnosis and treatment data, a pre-trained artificial intelligence-based osteoporosis risk assessment model is used to determine a second risk score for the second user suffering from osteoporosis and send it to the second user terminal.

2. The method according to claim 1, characterized in that The method further comprises: If the diagnosis and treatment data is found, the first risk score is sent to the first user terminal except the second user; If no diagnosis and treatment data is found, the first risk score is sent to all first user terminals.

3. The method according to claim 2, characterized in that in, Pushing a corresponding pre-designed osteoporosis risk questionnaire to the first user based on the first user's gender and age information; The step of screening a second user with a potential risk of osteoporosis from the first user according to the first risk score includes: Determining a risk threshold corresponding to the gender type and age group according to the gender type and age group of the first user; If the first risk score of the first user is higher than the corresponding risk threshold, the first user is determined to be a second user with a potential risk of osteoporosis.

4. The method according to claim 3, characterized in that The method of determining, based on the diagnosis and treatment data, a second risk score for osteoporosis of the second user using a pre-trained artificial intelligence-based osteoporosis risk assessment model and sending the score to the second user terminal includes: classifying the diagnosis and treatment data into laboratory data and imaging data; inputting the test data into a pre-trained first osteoporosis risk assessment model based on artificial intelligence, and outputting a second test risk sub-score indicating that the second user suffers from osteoporosis; Inputting the image data into a pre-trained second osteoporosis risk assessment model based on artificial intelligence, and outputting a second image risk sub-score indicating that the second user suffers from osteoporosis; A second risk score for osteoporosis for the second user is calculated based on the second laboratory risk sub-score and the second imaging risk sub-score and sent to the second user terminal.

5. An artificial intelligence-based osteoporosis risk assessment system, characterized in that: The system comprises: A receiving module, configured to receive feedback information from a first user on an online osteoporosis risk questionnaire; a first determining module, configured to determine a first risk score for the first user suffering from osteoporosis based on the feedback information; a screening module, configured to screen a second user with a potential risk of osteoporosis from among the first users based on the first risk score; a search module, configured to obtain historical diagnosis and treatment information of the second user at each networked hospital, and search for diagnosis and treatment data related to osteoporosis diagnosis from the historical diagnosis and treatment information; The second determination module is used to determine the second risk score of the second user suffering from osteoporosis based on the diagnosis and treatment data and send it to the second user terminal using a pre-trained artificial intelligence-based osteoporosis risk assessment model if the diagnosis and treatment data is found.

6. The system according to claim 5, characterized in that The system further comprises: a first sending module, configured to send the first risk score to a first user terminal other than the second user if diagnosis and treatment data is found; The second sending module is configured to send the first risk score to all first user terminals if no diagnosis and treatment data is found.

7. The system according to claim 6, characterized in that in, Pushing a corresponding pre-designed osteoporosis risk questionnaire to the first user based on the first user's gender and age information; The screening module is specifically used for: Determining a risk threshold corresponding to the gender type and age group according to the gender type and age group of the first user; If the first risk score of the first user is higher than the corresponding risk threshold, the first user is determined to be a second user with a potential risk of osteoporosis.

8. The system according to claim 7, characterized in that The second determining module is specifically configured to: classifying the diagnosis and treatment data into laboratory data and imaging data; inputting the test data into a pre-trained first osteoporosis risk assessment model based on artificial intelligence, and outputting a second test risk sub-score indicating that the second user suffers from osteoporosis; Inputting the image data into a pre-trained second osteoporosis risk assessment model based on artificial intelligence, and outputting a second image risk sub-score indicating that the second user suffers from osteoporosis; A second risk score for osteoporosis for the second user is calculated based on the second laboratory risk sub-score and the second imaging risk sub-score and sent to the second user terminal.

9. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program is configured to execute the method according to any one of claims 1 to 4 when run.

10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the method according to any one of claims 1 to 4.

Images