Dynamic health risk assessment method based on multi-source heterogeneous data

Abstract

The present application relates to a kind of dynamic health risk assessment methods based on multi-source heterogeneous data, belong to data processing field.The method is applied to physical examination system, and the method comprises: physical examination system obtains the portrait data of user and M candidate physical examination schemes selected by user, any two candidate physical examination schemes in M candidate physical examination schemes contain different examination items, and M is integer greater than 1;Physical examination system is based on the portrait data of user, deduces the multi-source heterogeneous data of each candidate physical examination scheme in M candidate physical examination schemes adopted by user, and a total of M multi-source heterogeneous data is obtained.

Description

Technical Field

[0001] This invention belongs to the field of data processing and relates to a dynamic health risk assessment method based on multi-source heterogeneous physical examination data. Background Technology

[0002] Currently, medical examination institutions typically offer users a variety of fixed packages (such as basic onboarding package, standard annual package, cardiovascular and cerebrovascular special package, early cancer screening package, etc.), and users can choose one or more packages for medical examination based on their own feelings or the institution's recommendation.

[0003] While this "package-style" physical examination model is convenient for institutions to manage and price, it is not flexible enough and cannot accurately meet the needs of users. Summary of the Invention

[0004] In view of this, in order to solve the above problems, the present invention provides a dynamic health risk assessment method based on multi-source heterogeneous physical examination data.

[0005] To achieve the above objectives, the present invention provides the following technical solution: Firstly, a dynamic health risk assessment method based on multi-source heterogeneous physical examination data is provided. The method is applied to a physical examination system and includes: the physical examination system acquiring user profile data and M candidate physical examination plans selected by the user, wherein any two candidate physical examination plans contain different examination items, and M is an integer greater than 1; based on the user profile data, the physical examination system derives multi-source heterogeneous physical examination data for each of the M candidate physical examination plans, resulting in a total of M multi-source heterogeneous physical examination data; the physical examination system outputs the dynamic health risk assessment results corresponding to each of the M multi-source heterogeneous physical examination data.

[0006] Therefore, this technical solution moves the prediction of physical examination results from "after the examination is completed" to "before the selection of a plan." Users no longer need to blindly guess which of multiple fixed packages is more suitable for them, but can intuitively see the dynamic health risk assessment results that different physical examination plans may detect, and make informed comparisons accordingly. Compared with the traditional "pay first, know the results later" model, this invention solves the problem of information asymmetry in physical examination decision-making, enabling users to select the physical examination plan that best meets their own health needs. This not only improves the targeting of physical examinations, but also reduces unnecessary examination items, optimizes the allocation efficiency of physical examination resources, and improves the user experience.

[0007] Optionally, the user's profile data includes the user's basic physical characteristics data. Based on the user's profile data, the physical examination system derives multi-source heterogeneous physical examination data for each of the M candidate physical examination plans adopted by the user. This includes: the physical examination system derives multi-source heterogeneous physical examination data for each of the M candidate physical examination plans adopted by the user based on the user's basic physical characteristics data and the basic physical characteristics rule knowledge base.

[0008] Therefore, even when users lack historical medical examination data (such as during their first examination or when changing institutions), this technical solution, through basic vital sign data (age, BMI, smoking and drinking history, family medical history, etc.) combined with a basic vital sign rule knowledge base, can still reasonably predict the possible detection results of different medical examination programs. This solves the "cold start" problem, ensuring that all users—regardless of whether they have historical records—can receive the prediction service. Compared to existing solutions that rely solely on historical data, this solution covers a wider user group, and the prediction results still possess medical rationality.

[0009] Optionally, the M candidate physical examination plans correspond one-to-one with the M basic vital sign rule knowledge bases. Any two basic vital sign rule knowledge bases contain different basic vital sign rules. Based on the user's basic vital sign data and the basic vital sign rule knowledge bases, the physical examination system deduces multi-source heterogeneous physical examination data for each of the M candidate physical examination plans adopted by the user. This includes: for the i-th candidate physical examination plan among the M candidate physical examination plans, where i is an integer from 1 to M: the physical examination system obtains the multi-source heterogeneous physical examination data for the user adopting the i-th candidate physical examination plan by matching the user's basic vital sign data with the basic vital sign rule knowledge base corresponding to the i-th candidate physical examination plan.

[0010] This shows that different health checkup plans focus on different health dimensions (e.g., cardiovascular and cerebrovascular packages focus on blood pressure and blood lipids, while tumor packages focus on biomarkers and CT scans). This technical solution configures a dedicated rule knowledge base for each candidate plan independently. During the deduction process, only the rule set related to that plan is called, achieving a precise "plan-rule" mapping. At the same time, the modular design facilitates subsequent maintenance—institutions only need to optimize the rule base for a specific plan without affecting the deduction logic of other plans.

[0011] Optionally, the physical examination system obtains multi-source heterogeneous physical examination data for the user using the i-th candidate physical examination plan by matching the user's basic vital sign data with the basic vital sign rule knowledge base corresponding to the i-th candidate physical examination plan. This includes: the physical examination system matching the user's basic vital sign data with the basic vital sign rule knowledge base corresponding to the i-th candidate physical examination plan to determine that there are Ni basic vital sign rules applicable to the user's basic vital sign data in the basic vital sign rule knowledge base corresponding to the i-th candidate physical examination plan, where Ni is an integer greater than 1; and the physical examination system determining the result description information in the Ni basic vital sign rules as the multi-source heterogeneous physical examination data for the user using the i-th candidate physical examination plan.

[0012] Therefore, this technical solution clearly defines the transformation logic from "rule matching" to "data output": the system does not attempt to generate specific detection values ​​(such as "blood glucose 6.5 mmol / L"), but rather outputs the pre-defined result descriptions in the rules (such as "abnormal fasting blood glucose may be detected"). This inference method based on rule result descriptions avoids complex numerical prediction models, reduces the difficulty of system implementation, and is more user-friendly and easier to understand for ordinary users. Furthermore, by statistically analyzing the number of applicable rules, the system can implicitly evaluate the richness and confidence of the inference—the more applicable rules, the closer the connection between the user and the solution, and the more reliable the inference results.

[0013] Optionally, the user's profile data includes the user's basic physical characteristics data and the user's historical physical examination data. Based on the user's profile data, the physical examination system derives multi-source heterogeneous physical examination data for each of the M candidate physical examination plans. This includes: the physical examination system derives multi-source heterogeneous physical examination data for each of the M candidate physical examination plans based on the user's basic physical characteristics data, the user's historical physical examination data, and the physical characteristics baseline rule knowledge base.

[0014] Therefore, when users possess both basic vital sign data and historical physical examination data, this technical solution utilizes individual health trends (such as gradually increasing blood pressure and blood sugar fluctuation patterns) to make more accurate predictions. Compared to predictions using only static profiles, the dual input of "individual baseline + static profile" after incorporating historical data significantly improves the accuracy and personalization of the predictions. The richer the user's historical data, the closer the prediction results are to the actual physical examination results, thereby enhancing the user's trust in the prediction results and providing a more powerful reference for decision-making.

[0015] Optionally, each of the M candidate physical examination schemes corresponds one-to-one with an M physical characteristic baseline rule knowledge base. The physical characteristic baseline rules contained in any two of the M physical characteristic baseline rule knowledge bases are different. Based on the user's basic physical characteristic data, the user's historical physical examination data, and the physical characteristic baseline rule knowledge base, the physical examination system deduces multi-source heterogeneous physical examination data for each of the M candidate physical examination schemes adopted by the user. This includes: for the i-th candidate physical examination scheme among the M candidate physical examination schemes, where i is an integer from 1 to M: the physical examination system obtains the multi-source heterogeneous physical examination data for the user adopting the i-th candidate physical examination scheme by matching the user's basic physical characteristic data and the user's historical physical examination data with the physical characteristic baseline rule knowledge base corresponding to the i-th candidate physical examination scheme.

[0016] This reveals fundamental differences in the reliance on and utilization of historical examination data across different health checkup plans. For instance, the "liver function retest package" focuses on the trends of ALT and AST levels, while the "bone density package" prioritizes age and previous bone density test results. This technical solution, by independently configuring a baseline rule knowledge base for vital signs for each plan, enables the system to utilize historical data in a customized manner, avoiding a "one-size-fits-all" approach to trend analysis. This improves the relevance of the analysis and reduces the interference of irrelevant data on the results.

[0017] Optionally, the physical examination system obtains multi-source heterogeneous physical examination data for the user using the i-th candidate physical examination plan by matching the user's basic vital sign data and historical physical examination data with the knowledge base of vital sign baseline rules corresponding to the i-th candidate physical examination plan. This includes: the physical examination system determining the variation baselines of the user's K vital sign indicators based on the user's historical physical examination data, where K is an integer greater than 1; the physical examination system determining that there are Nij vital sign baseline rules applicable to the user's basic vital sign data and the j-th vital sign indicator among the K vital sign indicators by matching the user's basic vital sign data and the j-th vital sign indicator with the knowledge base of vital sign baseline rules corresponding to the i-th candidate physical examination plan, where j is an integer from 1 to K and Nij is an integer greater than 1; and determining the result description information in the Nij vital sign baseline rules as the multi-source heterogeneous physical examination data for the user using the i-th candidate physical examination plan.

[0018] Therefore, this technical solution adopts a refined matching method of "indicator-by-indicator and rule-by-rule": First, the baseline of change for each vital sign indicator is determined based on historical data (trend, fluctuation range, recent value, etc.). Then, for each indicator, the user's basic vital sign data and the baseline of change for that indicator are matched with the rule knowledge base, and the result description information of all matching rules is summarized. This indicator-level matching granularity allows the inference results to be specific to which indicator may have what kind of abnormality (e.g., "systolic blood pressure continues to rise, predicting that this examination may have entered stage 1 hypertension"), providing users with highly interpretable decision-making basis, rather than a general risk level.

[0019] Optionally, the user's basic vital signs data may include at least some of the following: age, gender, height, weight, body mass index (BMI), smoking status, frequency of alcohol consumption, dietary habits, weekly exercise duration, sleep duration, self-rated stress level, medical history of immediate family members, or history of previously diagnosed diseases.

[0020] Therefore, the basic vital signs data (age, gender, BMI, smoking and drinking habits, exercise and sleep patterns, family medical history, past medical history, etc.) upon which this technical solution relies can all be obtained through a simple questionnaire or registration process, without the need for any medical equipment intervention. For users without historical data, these fields constitute the entire basis for the inference; for users with historical data, these fields serve as risk correction factors (e.g., smoking history will increase the risk probability in the inference of lung-related indicators). This dataset balances accessibility and medical relevance, ensuring the feasibility of the method in the actual operation of medical examination institutions without the need for additional hardware investment.

[0021] Optionally, after outputting the dynamic health risk assessment results corresponding to each of the multiple multi-source heterogeneous physical examination data, the method further includes: in response to the user's operation, determining the user's target physical examination plan from multiple candidate physical examination plans.

[0022] Therefore, this technical solution, after outputting the simulation results of multiple schemes, allows users to actively select one or more schemes based on the comparison information. The system then directly uses this selection result for subsequent physical examination appointments and process scheduling. This completes the business loop from "simulation and comparison" to "decision execution," avoiding the inconvenience of users switching between different systems and improving the user experience.

[0023] Secondly, a health checkup system is provided, configured as follows: the system acquires user profile data and M candidate health checkup plans selected by the user, wherein any two candidate health checkup plans contain different examination items, and M is an integer greater than 1; based on the user profile data, the system deduces multi-source heterogeneous health checkup data for each of the M candidate health checkup plans, resulting in a total of M multi-source heterogeneous health checkup data; the system outputs dynamic health risk assessment results corresponding to each of the M multi-source heterogeneous health checkup data.

[0024] The objectives and other advantages of this invention can be realized and obtained through the following description. Attached Figure Description

[0025] To make the objectives, technical solutions, and advantages of the present invention clearer, the preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings, wherein: Figure 1 A schematic diagram of the architecture of a physical examination system provided by the present invention; Figure 2 A flowchart of a dynamic health risk assessment method based on multi-source heterogeneous physical examination data provided by the present invention; Figure 3 This is a schematic diagram of the structure of a physical examination system provided by the present invention. Detailed Implementation

[0026] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other. The accompanying drawings are for illustrative purposes only, representing only schematic diagrams and not actual physical objects, and should not be construed as limiting the present invention. To better illustrate the embodiments of the present invention, some parts in the drawings may be omitted, enlarged, or reduced, and do not represent the actual product form.

[0027] like Figure 1 As shown in the figure, this application provides a physical examination system, which mainly includes a user interaction module (UIM) and a processing module (PM).

[0028] The user interaction module provides users with an interactive interface for selecting medical examination plans, displaying comparison results, and confirming the final plan. In its implementation, this module can be deployed in various forms: for example, integrated into a self-service terminal (Kiosk) in a medical examination institution, allowing users to complete operations via a touchscreen; or running as a mobile application (App) on the user's smartphone, supporting iOS and Android systems; or via a WeChat Mini Program or a web portal, accessible through a browser. Regardless of the form, the core function of the user interaction module remains consistent: receiving user-input profile data (such as basic vital signs information, uploaded or authorized historical medical examination data), displaying multiple candidate medical examination plans for the user to select, sending the list of selected candidate plans to the processing module, and presenting a visual comparison report of the results of each plan returned by the processing module.

[0029] The processing module is the logical core of the system, responsible for storing and managing user profile data, maintaining the basic vital sign rule knowledge base and the vital sign baseline rule knowledge base, performing inference calculations, and generating dynamic health risk assessment results. In terms of deployment, the processing module is typically deployed on a cloud server, utilizing elastic computing resources to support concurrent requests from multiple users. For medical examination institutions with high data security requirements, a private deployment method using on-premises servers can also be adopted, with all data stored within the institution's internal network. The processing module internally comprises several sub-units: a rule knowledge base management unit, an inference engine unit, a result generation unit, and a database unit (used to store user profile data, historical medical examination records, and inference logs).

[0030] Communication between the user interaction module and the processing module uses standard Internet protocols. When the user interaction module runs as a mobile application or webpage, they use Hypertext Transfer Protocol Secure (HTTPS) for RESTful API calls to ensure the confidentiality and integrity of data transmission. For interactive scenarios requiring real-time feedback (such as instantly refreshing comparison results after a user selects different packages), the WebSocket full-duplex communication protocol can be used to reduce response latency. When the user interaction module is deployed in a self-service terminal within a medical examination institution, the terminal connects to the local processing module via the institution's local area network (LAN) or communicates with the cloud processing module via a security gateway. All communication interfaces are designed in a stateless request-response model and use JSON (JavaScript Object Notation) format to encapsulate data, facilitating parsing and expansion across different platforms.

[0031] Through the above modular design, the user interaction module focuses on the front-end experience, while the processing module focuses on the back-end logic and data storage. The two are loosely coupled and work together, which not only facilitates independent upgrades and maintenance of the system, but also allows medical examination institutions to flexibly choose deployment solutions according to their own scale (such as small institutions can directly use cloud services, while large institutions can deploy privately to meet data compliance requirements).

[0032] like Figure 2 As shown in the figure, this application provides a dynamic health risk assessment method based on multi-source heterogeneous physical examination data. This method is applied to the above-mentioned physical examination system, and the specific process of this method is as follows: S201, the physical examination system obtains the user's profile data and the M candidate physical examination plans selected by the user. Any two candidate physical examination plans among the M candidate physical examination plans contain different examination items, and M is an integer greater than 1.

[0033] User profile data includes the user's basic physical characteristics. Alternatively, user profile data includes the user's basic physical characteristics and the user's historical medical examination data.

[0034] Specifically, the user interaction module of the health checkup system first presents a user profile data collection interface. For first-time users or those with insufficient historical data, the system guides them to fill in basic physical characteristics data, including but not limited to: age, gender, height, weight, body mass index (BMI), smoking status (e.g., never, occasionally, daily), alcohol consumption frequency (e.g., never, 1-2 times per week, more than 3 times per week), dietary habits (e.g., balanced, oily, vegetarian), weekly exercise duration (minutes), sleep duration (hours / day), self-rated mental stress level (e.g., low, medium, high), medical history of immediate family members (parents, siblings) (e.g., hypertension, diabetes, coronary heart disease, malignant tumors, etc.), and the user's own previously diagnosed medical history (e.g., hyperlipidemia, fatty liver, chronic gastritis, etc.). The above data can be collected through form input, sliding selection, or multiple-choice questions, and submitted after user confirmation.

[0035] For users who have already kept physical examination records at the physical examination institution, the system, after obtaining user authorization, automatically retrieves the user's past physical examination reports from the historical physical examination database as historical physical examination data. Historical physical examination data includes the dates of each physical examination, the test values ​​and reference ranges of various examination indicators, and the textual and graphical conclusions of imaging reports. In this case, the user's profile data is composed of both basic physical characteristic data and historical physical examination data; if the user has no historical physical examination data, the profile data only includes basic physical characteristic data.

[0036] After collecting or retrieving the profile data, the user interaction module displays a list of available candidate physical examination plans to the user. These candidate plans are pre-configured by the medical examination institution, with each plan corresponding to a fixed set of examination items. For example, a basic annual package may include: complete blood count, urinalysis, liver function, kidney function, four lipid profiles, fasting blood glucose, electrocardiogram, and abdominal ultrasound; a cardiovascular and cerebrovascular special package may additionally include: carotid ultrasound, echocardiography, homocysteine, and high-sensitivity C-reactive protein; a tumor early screening package may include: low-dose spiral CT, alpha-fetoprotein (AFP), carcinoembryonic antigen (CEA), and carbohydrate antigen 19-9 (CA19-9), etc. The user selects at least two candidate physical examination plans (M≥2) from the list simultaneously by checking boxes, and the examination items included in any two of the selected M plans are not exactly the same. After the user confirms the selection, the user interaction module packages the user's basic physical condition data (and any historical physical examination data that may exist) together with the identifiers or item lists of the selected M candidate physical examination plans and sends them to the processing module.

[0037] After receiving the above information, the processing module first performs a data integrity check: if necessary basic vital signs fields are missing (e.g., BMI or smoking status is not filled in), a prompt is returned through the user interaction module, requesting the user to fill in the missing information; if the data is complete, the user's profile data and candidate solution list are temporarily stored in memory or a temporary database for subsequent steps S202 to call.

[0038] S202, the physical examination system, based on the user's profile data, infers multi-source heterogeneous physical examination data for each of the M candidate physical examination plans, resulting in a total of M multi-source heterogeneous physical examination data.

[0039] It should be noted that the "multi-source heterogeneous physical examination data" obtained in this step is an intermediate result. That is, for each candidate physical examination plan, it is a set of descriptions of various examination indicators and their abnormal states that may be detected after the plan is implemented, rather than the final dynamic health risk assessment result. The final assessment result will be generated based on this intermediate result in subsequent step S203.

[0040] Scenario 1: The user's profile data only includes the user's basic physical characteristics data (i.e., the user has no historical physical examination data). In this scenario, the physical examination system, based on the user's basic vital signs data and a pre-configured basic vital signs rule knowledge base, deduces multi-source heterogeneous physical examination data for each of the M candidate physical examination plans adopted by the user.

[0041] Specifically, the medical examination institution independently configures a corresponding basic vital sign rule knowledge base for each candidate medical examination plan. Different candidate medical examination plans focus on different health dimensions, therefore the rules contained in their rule knowledge bases also differ. For example, the rule knowledge base corresponding to the "cardiovascular and cerebrovascular special package" mainly includes rules related to blood pressure, blood lipids, and heart function; while the rule knowledge base corresponding to the "early cancer screening package" mainly includes rules related to lung nodules and tumor markers. Each of the M candidate medical examination plans corresponds one-to-one with one of the M basic vital sign rule knowledge bases, and no two basic vital sign rule knowledge bases contain completely identical rules.

[0042] For the i-th candidate physical examination plan (where i is an integer from 1 to M) among M candidate plans, the physical examination system performs the following operations: It matches the user's basic vital signs data with each rule in the basic vital signs rule knowledge base corresponding to that plan, determining whether the user's data meets the condition part of the rule. Each rule adopts a "condition-conclusion" structure. The condition part describes a certain value or range of the user's basic vital signs data, and the conclusion part describes the abnormal indicators or items that may be detected under this physical examination plan.

[0043] For example, the basic vital signs rule knowledge base corresponding to the "Cardiovascular and Cerebrovascular Special Package" can be configured with the following rules: If the user is ≥45 years old and has a BMI ≥28, the conclusion is "high blood pressure and abnormal blood lipids may be detected"; If the smoking status is "daily smoking" and the age is ≥50 years, the conclusion is "carotid intima thickening or plaque may be detected"; If a family member has a history of hypertension and the BMI is ≥24, the conclusion is "It is recommended to focus on systolic and diastolic blood pressure". If the weekly exercise duration is less than 150 minutes and the self-rated mental stress level is "high", the conclusion is "possible detection of abnormal heart rate variability or ST-T changes on electrocardiogram".

[0044] Suppose a user's baseline physical characteristics are: age 52, BMI 29, smoking status "daily smoker," family history of hypertension, 90 minutes of exercise per week, and self-rated stress level "moderate." The health check system matches this data against the above rules one by one: the first rule is met (age ≥ 45 and BMI ≥ 28), the second rule is met (daily smoker and age ≥ 50), the third rule is met (family history of hypertension and BMI ≥ 24), and the fourth rule is not met (stress is "moderate" rather than "high"). Therefore, the system determines that there are Ni=3 rules in the baseline physical characteristics rule knowledge base applicable to this user. The health check system summarizes the result description information from these Ni rules (i.e., "possible detection of high blood pressure, abnormal blood lipids," "possible detection of carotid intima-media thickening or plaque," "recommendation to focus on systolic and diastolic blood pressure") as the multi-source heterogeneous health check data for this user using the i-th candidate health check plan (cardiovascular and cerebrovascular special package). For other candidate health checkup programs (such as early cancer screening packages), the health checkup system will independently execute the above matching process using its proprietary rule knowledge base to obtain another intermediate result. This process is repeated for M candidate programs, resulting in a total of M multi-source heterogeneous health checkup data.

[0045] Scenario 2: The user's profile data includes both the user's basic physical characteristics and the user's historical medical examination data. In this scenario, the health check system, based on the user's basic vital signs data, historical health check data, and a pre-configured baseline rule knowledge base, deduces multi-source heterogeneous health check data for each of the M candidate health check plans. Similar to scenario one, the M candidate health check plans correspond one-to-one with the M baseline rule knowledge bases, and any two baseline rule knowledge bases contain different rules to accommodate different ways of utilizing historical data for different plans.

[0046] In this invention, the so-called "variable baseline" refers to a set of parameters calculated based on the user's historical physical examination data, reflecting the historical variation pattern of a certain vital sign indicator. This parameter set is used to quantify the dynamic evolution characteristics of the indicator and is a key input for subsequent rule matching. The variable baseline includes at least the following: the most recent test value of the indicator, the trend of change of the test values ​​over time (e.g., stable, slowly rising, rapidly declining, significant fluctuations), whether it has exceeded the normal range and the number of times it has exceeded the standard, and the time interval between the most recent test and the current time. In some embodiments, the variable baseline may also include the seasonal fluctuation pattern of the indicator or the change pattern related to specific events (e.g., medication, surgery).

[0047] For the i-th candidate health checkup plan, the system first determines the baseline changes of the user's K key health indicators based on the user's historical health checkup data. The value of K is determined by the range of indicators that the health checkup plan focuses on. For example, from the user's historical health checkup data, the following baseline changes can be extracted: systolic blood pressure: "The values ​​measured in the past three years were 135 mmHg, 142 mmHg, and 148 mmHg, with a continuous upward trend, and the most recent value was 148 mmHg"; fasting blood glucose: "The values ​​measured in the past three years were 5.6 mmol / L, 5.9 mmol / L, and 6.1 mmol / L, with a slow upward trend, and the most recent value was 6.1 mmol / L"; low-density lipoprotein: "All values ​​in the past three years were within the normal range, with a stable trend."

[0048] Subsequently, the health check system matches the user's basic vital signs data and the baseline changes of each of the K vital signs indicators with the vital signs baseline rule knowledge base corresponding to the i-th candidate health check plan. Each rule in this knowledge base involves both the user's basic vital signs data and the baseline changes of one or more vital signs indicators in its condition part. For example, for the vital signs baseline rule knowledge base corresponding to the "Cardiovascular and Cerebrovascular Special Package," the following rules can be configured: Rule B1: If the baseline change in systolic blood pressure is "continuously rising" and the most recent measurement is ≥140 mmHg, the conclusion is "the systolic blood pressure in this examination may have entered stage 1 hypertension (140-159 mmHg)"; Rule B2: If the baseline change in fasting blood glucose is "slowly rising" and the most recent test value is ≥5.6 mmol / L, the conclusion is "the glycated hemoglobin may be slightly elevated in this test"; Rule B3: If the baseline change in LDL cholesterol is "continuously rising" and the user's age is ≥45 years, the conclusion is "LDL cholesterol may be excessive, indicating an increased risk of atherosclerosis"; Rule B4: If a user's BMI is ≥28 and their triglyceride levels show a "significant fluctuation" historical trend, the conclusion is "fatty liver may be detected by abdominal ultrasound".

[0049] During the matching process, the health check system iterates through K vital signs indicators one by one. For the j-th vital sign indicator (j is an integer from 1 to K), the system checks whether there exists a rule that uses its baseline change as a condition, and the user's basic vital sign data also meets other conditions of the rule. If it exists, the system records the conclusion description information corresponding to the rule. For each indicator, there may be 0, 1, or more rules that match successfully. The number of rules that match successfully for the j-th indicator under the i-th scheme is denoted as Nij (Nij is an integer ≥ 0). After iterating through all K indicators, the system summarizes all the conclusions of the successfully matched rules (a total of ∑_{j=1}^{K} Nij rules) as the multi-source heterogeneous health check data for the user using the i-th candidate health check scheme.

[0050] For example, a user's baseline physical characteristics are: age 48, BMI 26, no smoking history; historical physical examination data shows: systolic blood pressure has been continuously rising (most recently 148 mmHg), fasting blood glucose has been slowly rising (most recently 6.1 mmol / L), low-density lipoprotein (LDL) has been stable and normal, and triglycerides have a stable historical trend. For the "cardiovascular and cerebrovascular special package," the physical examination system matches each item: for systolic blood pressure (j=1), rule B1 matches successfully, generating 1 conclusion; for fasting blood glucose (j=2), rule B2 matches successfully, generating 1 conclusion; for LDL (j=3), its baseline is stable and normal, not meeting the condition of rule B3 (requiring continuous rise), so no rule matches; for triglycerides (j=4), its trend is stable, not meeting the condition of rule B4 (requiring significant fluctuation), also so no rule matches. Therefore, a total of 2 rule conclusions are obtained. These conclusions collectively constitute the multi-source heterogeneous physical examination data for this user's cardiovascular and cerebrovascular special package. For example, they can be expressed as: {"The systolic blood pressure in this examination may be grade 1 hypertension"; "The glycated hemoglobin in this examination may be slightly elevated"}. This intermediate result only includes a prediction of the probability of abnormality of specific indicators and does not include a comprehensive risk score or risk level, which will be left for further risk assessment and visualization output by S203.

[0051] For each of the M candidate physical examination plans, the physical examination system independently executes the aforementioned derivation process based on the baseline rule knowledge base of vital signs, ultimately obtaining M multi-source heterogeneous physical examination data. These intermediate results will be temporarily stored, along with a confidence level label for each conclusion (e.g., based on the completeness of the historical data on which the rule relies and the clarity of the trend, it can be labeled as "high confidence", "medium confidence", or "based on population statistics"), so that the credibility of the prediction can be shown when presented to the user in S203.

[0052] S203, the physical examination system outputs dynamic health risk assessment results corresponding to M multi-source heterogeneous physical examination data.

[0053] The health checkup system transforms the M multi-source heterogeneous health checkup data obtained in S202 (i.e., the set of predicted conclusions corresponding to each candidate health checkup plan) into dynamic health risk assessment results that users can intuitively understand, and displays them visually through the user interaction module. Specifically, for each candidate health checkup plan, the processing module labels each predicted conclusion in its multi-source heterogeneous health checkup data with a risk level and confidence level, generating a structured risk assessment result.

[0054] For example, if a candidate protocol's multi-source heterogeneous physical examination data includes the conclusion that "the systolic blood pressure in this examination may be grade 1 hypertension," the processing module can label its risk level as "medium-high risk" based on a medical knowledge base, and attach a confidence level based on historical data trends (e.g., "high confidence"). The conclusion that "the glycated hemoglobin in this examination may be slightly elevated" can be labeled as "medium risk" with a confidence level of "medium." Conclusions derived solely from basic physical examination rules (e.g., "high blood pressure and abnormal blood lipids may be detected") are labeled as "requiring attention" with a confidence level of "based on population statistics." The processing module can also generate a comprehensive risk warning for each candidate protocol (e.g., "This protocol is expected to detect 2 medium-high risk abnormalities and 1 abnormality requiring attention"), without altering the independence of each conclusion.

[0055] Subsequently, the user interaction module presents the risk assessment results of the M candidate medical examination options to the user in the form of a visual comparison report. This comparison report includes at least one or more of the following presentation methods: Table Comparison: The table uses the plan as columns and the indicators / conclusions as rows. Each cell displays the prediction conclusion, risk level and confidence level of the plan for the indicator, and uses different colors to distinguish the level of risk (red indicates high risk, yellow indicates medium risk, and gray indicates that attention is needed or that it cannot be predicted).

[0056] Radar chart comparison: Several health dimensions are preset (such as cardiovascular health, metabolic health, tumor risk, liver and kidney function, etc.). Based on the coverage strength and abnormal prediction probability of the conclusions derived by each plan in each dimension, polygons of each plan are drawn, so that users can intuitively compare the "detection ability" of different plans in different health dimensions.

[0057] Difference Highlighting Comparison: Automatically identifies differences in conclusions between different solutions, such as "Solution A can detect the risk of carotid plaques, while Solution B cannot," and displays these differences in highlighted font or icons to help users quickly locate key distinctions.

[0058] Timeline simulation (optional): For users with historical data, attach the historical trend curve of the indicator next to the simulation conclusion, and mark the possible change nodes in this prediction.

[0059] The user interaction module also allows users to click on any prediction conclusion and pop up a detailed explanation window to explain the reasoning behind the conclusion (e.g., "Based on your continuous upward trend of systolic blood pressure over the past three years (135→142→148 mmHg) and family history of hypertension, there is a high probability that this examination will result in stage 1 hypertension").

[0060] After outputting the dynamic health risk assessment results corresponding to each of the multiple multi-source heterogeneous physical examination data, the method further includes: in response to the user's operation, determining the user's target physical examination plan from multiple candidate physical examination plans.

[0061] Specifically, the user interaction module provides a plan selection interface below the comparison report, where users can select one or more candidate medical examination plans as the final target plan. The system supports the following operation methods: users click the "Select this plan" button on a plan card, or select by checkbox and then click "Confirm Appointment". If the user selects multiple plans, the system can automatically merge the examination items included in these plans, remove duplicates, and generate a comprehensive medical examination application form. In response to the user's confirmation operation, the user interaction module sends the identifier of the target medical examination plan to the appointment management system of the medical examination institution, triggering the subsequent medical examination process arrangement (such as department scheduling, payment guidance, pre-examination precautions, etc.). At the same time, the system can record the user's selection results and compare them with the deduction conclusion of S202 for subsequent rule knowledge base optimization (for example, to count whether the plan finally selected by the user is consistent with the "plan with the most high-risk conclusions" deduced by the system, and to evaluate the reference value of the deduction).

[0062] In summary, this technical solution moves the prediction of physical examination results from "after the examination is completed" to "before the selection of a plan." Users no longer need to blindly guess which of multiple fixed packages is more suitable for them, but can intuitively see the dynamic health risk assessment results that different physical examination plans may detect, and make informed comparisons accordingly. Compared with the traditional "pay first, know the results later" model, this invention solves the problem of information asymmetry in physical examination decision-making, enabling users to select the physical examination plan that best meets their own health needs. This not only improves the targeting of physical examinations, but also reduces unnecessary examination items, optimizes the allocation efficiency of physical examination resources, and improves the user experience.

[0063] Figure 3 This is a schematic diagram of the structure of a physical examination system provided in an embodiment of this application. Exemplarily, the physical examination system can be a terminal, or a chip (system) or other component or part that can be disposed on the terminal. Figure 3As shown, the physical examination system 200 may include a processor 201. Optionally, the physical examination system 200 may also include a memory 202 and / or a transceiver 203. The processor 201 is coupled to the memory 202 and the transceiver 203, for example, via a communication bus.

[0064] The following is combined Figure 3 A detailed introduction to each component of the physical examination system 200: The processor 201 is the control center of the physical examination system 200. It can be a single processor or a collective term for multiple processing elements. For example, the processor 201 can be one or more central processing units (CPUs), application-specific integrated circuits (ASICs), or one or more integrated circuits configured to implement the embodiments of this application, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).

[0065] Optionally, the processor 201 can perform various functions of the physical examination system 200 by running or executing software programs stored in the memory 202 and calling data stored in the memory 202, such as performing the aforementioned functions. Figure 2 The method shown.

[0066] In a specific implementation, as one example, the processor 201 may include one or more CPUs, for example... Figure 3 CPU0 and CPU1 are shown in the diagram.

[0067] In a specific implementation, as one example, the physical examination system 200 may also include multiple processors, for example... Figure 3 The processor 201 shown is an example. Each of the processors 201 can be a single-core processor or a multi-core processor. Here, "processor" can refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0068] The memory 202 is used to store the software program that executes the solution of this application, and is controlled by the processor 201 to execute it. The specific implementation method can be referred to the above method embodiment, and will not be repeated here.

[0069] Optionally, the memory 202 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory 202 may be integrated with the processor 201 or exist independently, and may be accessed through the interface circuit of the system 200. Figure 3 (Not shown in the image) is coupled to processor 201, but this embodiment does not specifically limit this.

[0070] Transceiver 203 is used for communication with other medical examination systems. For example, if medical examination system 200 is a terminal, transceiver 203 can be used to communicate with a network device or with another terminal device. Alternatively, if medical examination system 200 is a network device, transceiver 203 can be used to communicate with a terminal or with another network device.

[0071] Optionally, transceiver 203 may include a receiver and a transmitter. Figure 3 (Not shown separately). The receiver is used to implement the receiving function, and the transmitter is used to implement the transmitting function.

[0072] Optionally, the transceiver 203 can be integrated with the processor 201, or it can exist independently and be connected to the interface circuit of the medical examination system 200. Figure 3 (Not shown in the image) is coupled to processor 201, but this embodiment does not specifically limit this.

[0073] Understandable Figure 3 The structure of the medical examination system 200 shown in the figure does not constitute a limitation on the medical examination system. The actual medical examination system may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0074] Furthermore, the technical effects of the physical examination system 200 can be referred to the technical effects of the methods described in the above-described embodiments, and will not be repeated here.

[0075] It should be understood that the processor in the embodiments of this application can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0076] It should also be understood that the memory in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0077] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0078] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0079] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of 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 a single item or multiple items.

[0080] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply 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 this application.

[0081] Those skilled in the art will recognize that the units and algorithm steps of the various examples 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 implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0082] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0083] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0084] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0085] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0086] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a 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 to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0087] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A dynamic health risk assessment method based on multi-source heterogeneous physical examination data, characterized in that, The method is applied to a physical examination system, and the method includes: The physical examination system acquires the user's profile data and the M candidate physical examination plans selected by the user. Any two candidate physical examination plans among the M candidate physical examination plans contain different examination items, and M is an integer greater than 1. Based on the user's profile data, the physical examination system deduces multi-source heterogeneous physical examination data for each of the M candidate physical examination schemes, resulting in a total of M multi-source heterogeneous physical examination data. The physical examination system outputs the dynamic health risk assessment results corresponding to each of the M multi-source heterogeneous physical examination data.

2. The method according to claim 1, characterized in that, The user profile data includes the user's basic vital signs data. Based on the user profile data, the health check system derives multi-source heterogeneous health check data for each of the M candidate health check plans, including: The physical examination system, based on the user's basic vital signs data and basic vital signs rule knowledge base, deduces multi-source heterogeneous physical examination data for each of the M candidate physical examination schemes adopted by the user.

3. The method according to claim 2, characterized in that, The M candidate physical examination plans correspond one-to-one with M basic vital sign rule knowledge bases. Any two of the M basic vital sign rule knowledge bases contain different basic vital sign rules. Based on the user's basic vital sign data and the basic vital sign rule knowledge bases, the physical examination system derives multi-source heterogeneous physical examination data for each of the M candidate physical examination plans adopted by the user, including: For the i-th candidate physical examination plan among the M candidate physical examination plans, where i is an integer from 1 to M: The physical examination system obtains multi-source heterogeneous physical examination data of the user using the i-th candidate physical examination plan by matching the user's basic vital sign data with the basic vital sign rule knowledge base corresponding to the i-th candidate physical examination plan.

4. The method according to claim 3, characterized in that, The physical examination system obtains multi-source heterogeneous physical examination data of the user using the i-th candidate physical examination plan by matching the user's basic vital sign data with the basic vital sign rule knowledge base corresponding to the i-th candidate physical examination plan, including: The physical examination system determines that there are Ni basic physical characteristic rules applicable to the user's basic physical characteristic data in the basic physical characteristic rule knowledge base corresponding to the i-th candidate physical examination plan by matching the user's basic physical characteristic data with the basic physical characteristic rule knowledge base corresponding to the i-th candidate physical examination plan, where Ni is an integer greater than 1; The physical examination system determines the result description information in the Ni basic vital signs rules as the multi-source heterogeneous physical examination data for the user to adopt the i-th candidate physical examination plan.

5. The method according to claim 1, characterized in that, The user profile data includes the user's basic vital signs data and the user's historical physical examination data. Based on the user profile data, the physical examination system derives multi-source heterogeneous physical examination data for each of the M candidate physical examination plans, including: The physical examination system, based on the user's basic vital signs data, the user's historical physical examination data, and the vital signs baseline rule knowledge base, deduces multi-source heterogeneous physical examination data for each of the M candidate physical examination schemes adopted by the user.

6. The method according to claim 5, characterized in that, The M candidate physical examination plans correspond one-to-one with M physical characteristic baseline rule knowledge bases. Any two physical characteristic baseline rule knowledge bases contain different physical characteristic baseline rules. Based on the user's basic physical characteristic data, the user's historical physical examination data, and the physical characteristic baseline rule knowledge bases, the physical examination system derives multi-source heterogeneous physical examination data for each of the M candidate physical examination plans, including: For the i-th candidate physical examination plan among the M candidate physical examination plans, where i is an integer from 1 to M: The physical examination system obtains multi-source heterogeneous physical examination data of the user using the i-th candidate physical examination plan by matching the user's basic vital sign data and the user's historical physical examination data with the vital sign baseline rule knowledge base corresponding to the i-th candidate physical examination plan.

7. The method according to claim 6, characterized in that, The physical examination system obtains multi-source heterogeneous physical examination data of the user using the i-th candidate physical examination plan by matching the user's basic vital sign data and the user's historical physical examination data with the vital sign baseline rule knowledge base corresponding to the i-th candidate physical examination plan. This includes: The physical examination system determines the baseline changes of each of the user's K vital signs based on the user's historical physical examination data, where K is an integer greater than 1; The physical examination system determines that there are Nij baseline rules applicable to the user's basic vital signs data and the j-th vital sign indicator among the K vital sign indicators by matching the user's basic vital signs data and the j-th vital sign indicator with the vital sign baseline rule knowledge base corresponding to the i-th candidate physical examination plan. Here, j is an integer from 1 to K, and Nij is an integer greater than 1. The result description information in the Nij baseline rules is determined as the multi-source heterogeneous physical examination data for the user to adopt the i-th candidate physical examination plan.

8. The method according to any one of claims 2-7, characterized in that, The user's basic vital signs data include at least some of the following: age, gender, height, weight, body mass index (BMI), smoking status, frequency of alcohol consumption, dietary habits, weekly exercise duration, sleep duration, self-rated stress level, medical history of immediate family members, or history of previously diagnosed diseases.

9. The method according to claim 1, characterized in that, After outputting the dynamic health risk assessment results corresponding to each of the multiple multi-source heterogeneous physical examination data, the method further includes: In response to the user's operation, the user's target medical examination plan is determined from the plurality of candidate medical examination plans.

10. A physical examination system, characterized in that, The physical examination system is configured as follows: The physical examination system acquires the user's profile data and the M candidate physical examination plans selected by the user. Any two candidate physical examination plans among the M candidate physical examination plans contain different examination items, and M is an integer greater than 1. Based on the user's profile data, the physical examination system deduces multi-source heterogeneous physical examination data for each of the M candidate physical examination schemes, resulting in a total of M multi-source heterogeneous physical examination data. The physical examination system outputs the dynamic health risk assessment results corresponding to each of the M multi-source heterogeneous physical examination data.

Images