Inflammation marker-based chronic disease risk early warning method, system, equipment and medium

Abstract

The invention discloses a chronic disease risk early warning method, system and equipment based on inflammatory markers and a medium, and relates to the technical field of data processing. The method comprises the following steps: acquiring case information and sign information of a target patient, wherein the case information comprises a historical inflammation marker detection record, a chronic disease type and a medication scheme; according to historical inflammatory marker detection records, calculating reference values of multiple inflammatory markers; based on the chronic disease type, screening out an inflammatory marker combination, and correcting the reference value of each inflammatory marker in the inflammatory marker combination based on the medication scheme to obtain an initial early warning threshold group; compensating the initial early warning threshold value group in combination with the physical sign information to obtain a target early warning threshold value group; and collecting a current inflammatory marker detection value, and when any index in the inflammatory marker detection value is greater than or equal to a corresponding index threshold in the target early warning threshold group, generating chronic disease risk early warning information. By implementing the technical scheme provided by the invention, the accuracy of chronic disease risk early warning can be improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and specifically to a chronic disease risk warning method, system, device and medium based on inflammatory markers. Background Art

[0002] With the aging of the population and changes in lifestyle, the incidence of chronic diseases continues to rise. Chronic diseases are characterized by long courses and recurring attacks, and acute attacks often pose serious health threats to patients. Therefore, effective risk warnings and timely intervention for patients with chronic diseases are of great clinical significance.

[0003] Currently, medical institutions generally use inflammatory markers as important indicators for assessing the condition of patients with chronic diseases. In clinical practice, medical staff mainly use fixed reference value ranges for inflammatory markers to provide quantitative early warning of patients' chronic disease risks. However, in practice, due to individual differences among different patients, using only a unified reference value range for quantitative assessment often fails to reflect the actual risk situation of individual patients, thereby reducing the accuracy of chronic disease risk warnings. Summary of the Invention

[0004] The present application provides a chronic disease risk warning method, system, device and medium based on inflammatory markers, which can improve the accuracy of chronic disease risk warning.

[0005] In the first aspect, the present application provides a chronic disease risk early warning method based on inflammatory markers, comprising: Obtaining medical records and physical signs of target patients, including historical inflammatory marker test records, types of chronic diseases, and medication regimens; Calculating the baseline values ​​of multiple inflammatory markers corresponding to the target patient based on the historical inflammatory marker detection records; Based on the type of chronic disease, the target patient's inflammatory marker combination is screened out from each of the inflammatory markers, and the baseline value of each inflammatory marker in the inflammatory marker combination is corrected based on the medication regimen to obtain an initial warning threshold value group; Compensating the initial warning threshold value group in combination with the vital sign information to obtain a target warning threshold value group; The current inflammatory marker detection value of the target patient is collected, and the inflammatory marker detection value is compared with the target warning threshold group. When any indicator in the inflammatory marker detection value is greater than or equal to the corresponding indicator threshold in the target warning threshold group, chronic disease risk warning information of the target patient is generated.

[0006] In a second aspect of the present application, a chronic disease risk early warning system based on inflammatory markers is provided, the system comprising: An information acquisition module is used to obtain case information and physical sign information of the target patient, including historical inflammatory marker detection records, types of chronic diseases, and medication regimens; a threshold group determination module, configured to calculate the baseline values ​​of multiple inflammatory markers corresponding to the target patient based on the historical inflammatory marker detection records; screen out the inflammatory marker combination of the target patient from each of the inflammatory markers based on the type of chronic disease; and correct the baseline value of each inflammatory marker in the inflammatory marker combination based on the medication regimen to obtain an initial warning threshold group; A threshold group compensation module, configured to compensate the initial warning threshold group in combination with the vital sign information to obtain a target warning threshold group; The risk warning module is used to collect the current inflammatory marker detection value of the target patient and compare the inflammatory marker detection value with the target warning threshold group. When any indicator in the inflammatory marker detection value is greater than or equal to the corresponding indicator threshold in the target warning threshold group, chronic disease risk warning information of the target patient is generated.

[0007] In a third aspect of the present application, an electronic device is provided, comprising a memory, a processor, and a program stored in the memory and executable on the processor, wherein the program can implement a chronic disease risk warning method based on inflammatory markers when loaded and executed by the processor.

[0008] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements a chronic disease risk warning method based on inflammatory markers.

[0009] In summary, one or more technical solutions provided by this application have at least the following technical effects or advantages: By adopting the above technical solution, by obtaining the case information and physical sign information of the target patient, a personalized baseline value is calculated based on the historical inflammatory marker detection records, and a targeted inflammatory marker combination is screened out in combination with the type of chronic disease of the patient. At the same time, the impact of the medication regimen on the inflammatory marker is corrected to obtain the initial warning threshold group, and then compensated with the physical sign information to obtain the target warning threshold group. Finally, the current inflammatory marker detection value of the target patient is compared with the personalized target warning threshold group to determine whether a warning is needed, thereby avoiding the problem of insufficient warning accuracy caused by the use of a unified reference value range, and being able to establish personalized warning thresholds based on the individual characteristics of the patient, thereby improving the accuracy of chronic disease risk warnings. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1This is a flow chart of a chronic disease risk early warning method based on inflammatory markers provided in an embodiment of the present application; Figure 2 This is a schematic diagram of the structure of a chronic disease risk early warning system based on inflammatory markers provided in an embodiment of the present application; Figure 3 This is a structural diagram of an electronic device provided in an embodiment of the present application.

[0011] Description of reference numerals: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0012] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0013] In the description of the embodiments of this application, words such as "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "for example" or "for instance" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "for example" or "for instance" is intended to present the relevant concepts in a concrete manner.

[0014] In the description of the embodiments of the present application, the term "multiple" means two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0015] The present application embodiment provides a chronic disease risk warning method based on inflammatory markers. In one embodiment, please refer to Figure 1 , Figure 1This is a flow chart of a chronic disease risk warning method based on inflammatory markers provided in an embodiment of the present application. This method can be implemented by a computer program, which can be integrated into an application or run as an independent tool application. This method can also be implemented by a single-chip microcomputer or run on a chronic disease risk warning system based on inflammatory markers based on a von Neumann architecture. Specifically, this method can include the following steps: Step 101: Obtain the case information and physical sign information of the target patient, including historical inflammatory marker detection records, types of chronic diseases, and medication plans.

[0016] Among them, case information specifically includes: historical inflammatory marker test records, that is, various inflammatory marker data detected by the target patient during past medical treatment, including but not limited to the test values ​​and test time points of indicators such as C-reactive protein (CRP), erythrocyte sedimentation rate (ESR), and white blood cell count (WBC). These records reflect the historical change trend of the patient's inflammatory marker levels. The type of chronic disease refers to the type of chronic disease that the target patient has been diagnosed with, such as diabetes, hypertension, chronic kidney disease, etc. The medication plan contains information on various types of drugs that the target patient is taking, including detailed medication records such as drug name, dosage, and administration time.

[0017] Vital sign information refers to the reference indicators collected in real time by medical monitoring equipment, primarily including specific values ​​for physiological indicators such as body temperature, blood pressure, heart rate, and blood oxygen saturation. This vital sign data is used to compensate and adjust warning thresholds to improve the accuracy of warnings. Vital sign information reflects the patient's current physical condition and can promptly reflect changes in the patient's condition.

[0018] Specifically, the target patient's medical and vital signs information is first obtained. Medical information primarily includes historical inflammatory marker test records, chronic disease types, and medication regimens. Medical information is obtained from the hospital's electronic medical record system, including the patient's inflammatory marker test data for the past three years, including historical values ​​and corresponding test times for indicators such as C-reactive protein (CRP), erythrocyte sedimentation rate (ESR), and white blood cell count (WBC). Simultaneously, the patient's chronic disease diagnosis records are extracted from the medical record system to identify the specific chronic disease, such as diabetes, hypertension, or chronic kidney disease. Furthermore, the patient's medication regimen is also required, including detailed information such as the name, dosage, and dosing schedule of each medication. When acquiring vital signs information, medical monitoring equipment is primarily used to collect real-time vital sign data, including specific values ​​for reference indicators such as temperature, blood pressure, heart rate, and blood oxygen saturation. The purpose of obtaining this information is to establish a personalized basic data profile for the patient, providing the necessary data support for the subsequent calculation of baseline values ​​and warning thresholds for inflammatory markers. Comprehensive collection of this information helps the system fully account for individual patient differences and disease characteristics, thereby improving the accuracy and specificity of warnings. By integrating a patient's historical test records, disease information, medication usage, and vital signs data, a more comprehensive understanding of their health status can be achieved, laying the foundation for personalized chronic disease risk warnings. For example, for a patient diagnosed with diabetes, the system will obtain their blood sugar, glycosylated hemoglobin, and other inflammatory markers test records over the past three years. It will also record the type and dosage of their oral hypoglycemic medications, as well as their most recent vital signs such as blood pressure and heart rate. Comprehensive analysis of this information will help more accurately assess the patient's risk of disease progression.

[0019] Step 102: Calculate the baseline values ​​of multiple inflammatory markers corresponding to the target patient based on historical inflammatory marker detection records.

[0020] Among them, the baseline value of inflammatory markers refers to the personalized reference standard calculated based on the historical test records of the target patient, which reflects the typical level of inflammatory markers for the patient at a specific stage of the disease course.

[0021] Specifically, in order to accurately assess the chronic disease risk status of the target patient, it is necessary to first calculate the baseline value of each inflammatory marker. Since chronic diseases are characterized by cyclical attacks, there are significant differences in the levels of inflammatory markers in patients at different stages of the disease. Therefore, the present invention divides historical inflammatory marker detection records according to preset disease stages, including stable stage, relapse stage and remission stage. For each disease stage, the mean of the detection value of each inflammatory marker in that stage is calculated respectively, thereby obtaining the stage characteristic value of different disease stages. For example, for a patient's C-reactive protein detection record, its average level in the stable stage, relapse stage and remission stage is calculated respectively. After obtaining the current disease stage and the time of the most recent relapse of the target patient, the system selects the corresponding stage characteristic value based on the current disease stage and determines the correction coefficient based on the interval from the most recent relapse time. The introduction of the correction coefficient mainly takes into account that the length of time since the last relapse will affect the baseline level of the current inflammatory marker. The longer the time interval, the corresponding adjustment of the correction coefficient. Finally, the selected stage characteristic value is multiplied by the correction coefficient to obtain the baseline value of each inflammatory marker. This dynamic calculation method, based on disease stage and relapse time, more accurately reflects the target patient's baseline inflammatory marker levels at the current stage, avoiding the potential bias associated with using a fixed reference range and providing more reliable baseline data for subsequent risk warnings. For example, for a patient in the stable phase, if more than one year has passed since their last relapse, the correction factor will be appropriately lowered when calculating the baseline value to better reflect their current actual situation.

[0022] Based on the above embodiment, as an optional embodiment, in step 102: calculating the baseline values ​​of multiple inflammatory markers corresponding to the target patient based on the historical inflammatory marker detection records, this step may also include the following steps: Step 201: Divide the historical inflammatory marker detection records into detection sequences corresponding to a plurality of preset disease course stages, where the preset disease course stages include a stable stage, a relapse stage, and a remission stage.

[0023] Specifically, it is first necessary to divide the target patient's historical inflammatory marker test records into disease stages, because the patient's inflammatory marker levels at different stages of the disease course are significantly different. The patient's inflammatory marker test data for the past three years is obtained through the hospital's electronic medical record system. Combined with the patient's medical records, medication changes, clinical symptoms and other information, the test records are divided into three stages of test sequences: stable period, relapse period and remission period. For example, when the patient's symptoms are significantly aggravated, hospitalized or the drug dosage is significantly adjusted, the test data is divided into the relapse period test sequence; the test data that gradually returns to normal after the symptoms are controlled is divided into the remission period test sequence; the test data when the condition is stable and there is no obvious fluctuation is divided into the stable period test sequence. This data division method based on the disease course stage can more accurately reflect the changing characteristics of the patient's inflammatory markers at different stages.

[0024] Step 202: Calculate the mean of the inflammatory marker detection values ​​in the detection sequence corresponding to each disease course stage to obtain the stage characteristic value of the corresponding disease course stage.

[0025] Specifically, the system processes the data of the detection sequences of each stage of the disease course after division, calculates the arithmetic mean of the detection values ​​of inflammatory markers in each stage, and obtains the stage characteristic value of the corresponding stage of the disease course. During the specific calculation, the abnormal values ​​in the detection sequence are first eliminated, such as data that are abnormally increased or decreased due to complications or other emergencies. Then the mean is calculated for the remaining valid data to obtain the stage characteristic value that can represent the typical level of inflammatory markers in this stage. For example, the detection sequence of a patient's C-reactive protein in the stable period contains 10 detection records. After eliminating one abnormal value, the average of the remaining 9 detection values ​​is calculated as the stage characteristic value of the stable period. This method can effectively reduce the impact of accidental factors on the calculation of characteristic values ​​and improve the representativeness of the data.

[0026] Step 203: Obtain the current disease stage and the most recent relapse time of the target patient; determine the corresponding stage characteristic value based on the current disease stage, and determine the correction coefficient according to the interval from the most recent relapse time; multiply the stage characteristic value by the correction coefficient to obtain the baseline value of each inflammatory marker.

[0027] Specifically, the system first obtains the target patient's current disease stage and the specific time of their most recent relapse from the electronic medical record system. Based on the current disease stage, the corresponding stage characteristic value is selected as the basis for baseline value calculation. Simultaneously, a correction factor is determined based on the time interval since the most recent relapse. This correction factor is determined using a piecewise function. For example, if the time since relapse is within 3 months, the correction factor is set to 1.5; 1.2 for 3-6 months; 1.0 for 6-12 months; and 0.8 for more than 12 months. This correction mechanism accounts for the gradual change in a patient's risk of relapse over time. Finally, the selected stage characteristic value is multiplied by the correction factor to obtain a baseline value for inflammatory markers that reflects the patient's current condition. This dynamic calculation method not only considers the influence of disease stage but also reflects the role of time through the correction factor, ensuring that the resulting baseline value more accurately reflects the patient's actual condition.

[0028] Step 103: Based on the type of chronic disease, the inflammatory marker combination of the target patient is screened out from the various inflammatory markers, and the baseline value of each inflammatory marker in the inflammatory marker combination is corrected based on the medication regimen to obtain an initial warning threshold group.

[0029] The inflammatory marker panel refers to a collection of multiple inflammatory markers that are significantly correlated with the target patient's chronic disease type, selected from a pre-defined chronic disease-inflammatory marker database. For example, for a diabetic patient, their inflammatory marker panel might include indicators closely related to diabetes development and complication risk, such as glycated hemoglobin, C-reactive protein, and interleukin-6; while for a rheumatoid arthritis patient, their inflammatory marker panel might include specific indicators that reflect disease activity, such as rheumatoid factor, anti-cyclic citrullinated antibodies, and erythrocyte sedimentation rate.

[0030] The initial warning threshold group refers to the baseline value of each inflammatory marker in the inflammatory marker combination, which is corrected by the medication regimen to obtain a set of warning reference values. This set of warning reference values ​​takes into account the impact of the patient's current medication on the level of inflammatory markers. For example, if the patient is taking glucocorticoids, since this type of drug will inhibit the inflammatory response, the baseline value of C-reactive protein needs to be adjusted upward to obtain the initial warning threshold of this indicator. Each value in the initial warning threshold group is corrected for the impact of drugs, and these values ​​will serve as the basic data for subsequent physical sign compensation adjustments.

[0031] Specifically, because different chronic diseases have strong correlations with specific inflammatory markers, it is necessary to select the most indicative inflammatory marker combination based on the target patient's chronic disease type. The system first searches a pre-set chronic disease-inflammatory marker mapping database for a set of characteristic inflammatory markers corresponding to the target patient's chronic disease. For example, for patients with diabetes, the system prioritizes inflammatory markers closely associated with diabetes, such as glycated hemoglobin and C-reactive protein; for patients with rheumatoid arthritis, it focuses on specific markers such as rheumatoid factor and anti-cyclic citrullinated antibodies. After determining the inflammatory marker combination, the system calibrates the calculated baseline values ​​to account for the significant impact of the patient's current medication regimen on inflammatory marker levels. This calibration process first extracts the name, dosage, and duration of each medication from the medication regimen. Then, based on a pre-set drug impact model, the impact coefficient of each medication on the different inflammatory markers is calculated. This impact coefficient primarily takes into account factors such as the drug's mechanism of action, dosage, and duration of use. The baseline values ​​are then calculated with the corresponding drug impact coefficients to generate an initial warning threshold set that accounts for medication effects. For example, for patients taking glucocorticoids, their baseline C-reactive protein level needs to be adjusted upward based on the hormone dosage and duration of use to avoid false decreases caused by the inhibitory effects of the drug. This personalized indicator screening and medication impact correction method based on the type of chronic disease can more accurately reflect the patient's actual risk of disease progression, improving the pertinence and accuracy of early warnings.

[0032] Based on the above embodiment, as an optional embodiment, in step 103: based on the type of chronic disease, screening the target patient's inflammatory marker combination from various inflammatory markers, this step may also include the following steps: Step 301: Obtain a standard inflammatory marker combination template and a medication list for a target patient. The standard inflammatory marker combination template includes inflammatory marker combinations corresponding to multiple types of chronic diseases.

[0033] Specifically, the system first needs to obtain the standard inflammatory marker combination template and the target patient's medication list information. The standard inflammatory marker combination template is a preset database that stores the correspondence between different types of chronic diseases and their specific inflammatory markers. For example, for rheumatoid arthritis, the template contains specific indicators such as rheumatoid factor and anti-cyclic citrullinated antibodies; for systemic lupus erythematosus, it contains characteristic indicators such as antinuclear antibodies and complement C3. At the same time, the target patient's medication list is obtained through the hospital's electronic prescription system. The list records in detail all the medications currently taken by the patient, including drug name, specifications, usage and dosage, etc. The acquisition of these basic data provides the necessary reference basis for subsequent personalized indicator screening.

[0034] Step 302: In the standard inflammatory marker combination template, the first inflammatory marker corresponding to the chronic disease type of the target patient is screened out, and the second inflammatory marker of the target patient is determined based on the action type of each drug in the medication list.

[0035] Specifically, based on the specific type of chronic disease of the target patient, the system screens out the first inflammatory marker that is directly related to the chronic disease from the standard inflammatory marker combination template. These first inflammatory markers are core indicators that reflect the activity of this type of chronic disease. Subsequently, the system analyzes the type of action of each type of drug in the medication list, identifies drugs that may affect the level of inflammatory markers, and determines the second inflammatory marker that requires additional monitoring. For example, when a patient uses an immunosuppressant, it is necessary to increase the monitoring of indicators such as white blood cell count; when using certain biological agents, it is necessary to increase the monitoring of liver function-related indicators. This method of supplementing monitoring indicators based on medication conditions can more comprehensively assess the risks that may arise during drug treatment.

[0036] Step 303: Using the first inflammatory marker and the second inflammatory marker as an inflammatory marker combination for the target patient.

[0037] Specifically, the system integrates the primary and secondary inflammatory markers into a personalized inflammatory marker panel for the target patient. This panel includes both specific indicators that directly reflect chronic disease activity and auxiliary indicators related to medication safety monitoring. For example, for a patient with rheumatoid arthritis treated with biologics, the final inflammatory marker panel might include rheumatoid factor and anti-cyclic citrullinated antibodies (as the primary inflammatory marker) as well as transaminases and white blood cell count (as the secondary inflammatory markers). This combination, which considers both disease characteristics and the impact of medication, enables subsequent early warning assessments to more comprehensively and accurately reflect the patient's overall condition.

[0038] Based on the above embodiment, as an optional embodiment, in step 103: correcting the baseline value of each inflammatory marker in the inflammatory marker combination based on the medication regimen to obtain an initial warning threshold value group, this step may also include the following steps: Step 304: extracting the dosage and administration time of each drug from the medication regimen; and calculating the drug dosage curve corresponding to each drug based on the dosage and administration time of each drug.

[0039] Specifically, because drug concentrations in the body fluctuate dynamically over time, and these changes directly impact their regulatory effects on inflammatory markers, it is crucial to accurately understand the patterns of drug concentration changes in the body. The system first extracts detailed medication information from the target patient's medication regimen through the hospital's electronic prescription system, including each drug's name, strength, single dose, frequency, and start and end times. For example, for a patient taking 10 mg of oral prednisone daily, the system records the drug's dosing time (e.g., 8:00 AM each day) and duration of use. Subsequently, based on a pharmacokinetic model and incorporating each drug's pharmacokinetic parameters (such as bioavailability, time to peak concentration, and half-life), the system calculates the 24-hour blood concentration curve for each drug, known as the drug usage curve. The exponential equation C(t) = C0 × e^(-kt) is used to describe the drug elimination process, where C(t) is the drug concentration at time t, C0 is the peak concentration, and k is the elimination rate constant. For long-term medications, the drug accumulation effect must also be considered. By superimposing the concentration curves after multiple doses, the actual blood drug concentration curve under steady-state conditions is obtained. For example, if a patient takes prednisone once every 12 hours, their drug dosage curve over 24 hours will show a bimodal state, and the concentration curves after the two doses will be superimposed on each other. This dynamic concentration simulation based on the actual medication regimen can accurately reflect the real-time concentration level of the drug in the patient's body, providing a reliable data basis for subsequent evaluation of the drug's impact on inflammatory markers.

[0040] Step 305: Determine the time interval during which each inflammatory marker is affected by the drug according to the drug dosage curve.

[0041] Specifically, since the effects of different drugs on inflammatory markers are characterized by time delay and persistence, and this effect is closely related to drug concentration, it is necessary to accurately define the time interval of each drug's effect on each inflammatory marker. The system first establishes a drug-inflammatory marker impact relationship database, which stores the characteristic parameters of the effects of various drugs on different inflammatory markers, including onset time, peak time, duration of action, etc. Subsequently, the system combines the obtained drug dosage curve with the impact relationship parameters, and determines the impact time interval by setting the drug concentration threshold. In specific implementation, the system first determines the minimum effective concentration required for each drug to have a significant effect on inflammatory markers. When the concentration value on the drug dosage curve exceeds the threshold for the first time, it is marked as the starting time point of the impact; when the concentration value drops below the threshold, it is marked as the end time point of the impact. For example, for patients taking prednisone, their blood drug concentration reaches 5 ng / mL (minimum effective concentration) 2 hours after administration and begins to have a significant inhibitory effect on C-reactive protein. This effect continues until 20 hours after the drug concentration drops below 5 ng / mL. The system then determines the time interval during which the patient's C-reactive protein is affected by prednisone as 2-20 hours after administration. When a patient takes multiple medications simultaneously, the system considers the interactions between the drugs and, by superimposing the time intervals of influence of each drug, comprehensively determines the overall time range for which each inflammatory marker is affected. This method of defining time intervals based on the dynamic changes in drug concentration can more accurately reflect the actual impact of drugs on inflammatory markers, providing an accurate time reference for subsequent threshold correction.

[0042] Based on the above embodiment, as an optional embodiment, in step 305, determining the time interval during which each inflammatory marker is affected by the drug according to the drug dosage curve may further include the following steps: Step 315: Obtain the peak time points of the drug dosage curve; calculate the time intervals between adjacent peak time points.

[0043] Specifically, the system needs to identify each peak time point from the drug dosage curve. This is because the peak time point represents the time when the drug concentration reaches the local maximum, reflecting the period when the drug is most effective. In specific implementation, the system uses a numerical analysis method to calculate the first-order derivative of the drug dosage curve. The point where the derivative changes from positive to negative is the peak time point. For example, for a drug taken once every 12 hours, its drug dosage curve within 24 hours usually has two peaks, corresponding to the time when the drug reaches peak concentration after two doses. The system records these time points as t1, t2, etc. for subsequent time interval division.

[0044] Step 325: The midpoint of each time interval is used as the dividing point of the time interval.

[0045] Specifically, the system calculates the midpoint of the time interval between adjacent peak moments as the dividing point between different time intervals. This is done to divide the drug concentration curve according to the relative stability of the drug's intensity of action. For any adjacent peak moments ti and ti+1, the dividing point of the time interval is calculated as: dividing point = (ti+ti+1) / 2. For example, if the first peak occurs 2 hours after dosing (t1=2h) and the second peak occurs 14 hours after dosing (t2=14h), the dividing point between these two peaks is 8 hours after dosing. This division method based on the peak midpoint can better reflect the change process from rising to falling drug concentration.

[0046] Step 335: Divide the drug dosage curve into multiple time intervals based on each demarcation point.

[0047] Specifically, the system divides the entire drug dosage curve into multiple continuous time intervals based on the aforementioned demarcation points. The drug concentration change trend in each time interval is relatively consistent, which facilitates the subsequent quantitative analysis of the degree of impact. For example, for a drug dosage curve with two peaks within 24 hours, it will eventually be divided into four time intervals: the rising interval before the first peak, the falling interval from the first peak to the demarcation point, the rising interval from the demarcation point to the second peak, and the falling interval after the second peak. This time interval division method based on peak characteristics can more accurately characterize the dynamic change process of drug concentration and provide a more detailed time reference framework for the subsequent evaluation of the effect of drugs on inflammatory markers.

[0048] Step 306: Based on the time interval during which each inflammatory marker is affected by the drug, a weighted calculation is performed on the baseline value of each inflammatory marker to obtain an initial warning threshold value group.

[0049] Specifically, because the extent of a drug's impact on inflammatory markers varies over time, and the intensity of the impact varies across different time intervals, it is necessary to dynamically adjust the baseline values ​​of inflammatory markers based on the previously determined impact time intervals. The system first divides each impact time interval into multiple time segments, such as a two-hour segment, and calculates an impact weight coefficient based on the average drug concentration within that time segment. The impact weight coefficient is calculated using a piecewise function. When the drug concentration is between the minimum effective concentration and the maximum concentration, the weight coefficient is linearly correlated with the concentration; when the concentration exceeds the maximum concentration, the weight coefficient remains constant. For example, for patients taking prednisone, when the blood drug concentration is between 5 and 20 ng / mL, the impact weight coefficient for C-reactive protein is calculated as w = 0.1 × C (where C is the drug concentration); when the concentration exceeds 20 ng / mL, the weight coefficient is fixed at 2. The system then normalizes the weight coefficient for each time segment to obtain a standardized time weight. The baseline value of the inflammatory marker is multiplied by the standardized weight of the corresponding time segment, and the calculated results for all time segments are weighted and summed to obtain the initial warning threshold for the inflammatory marker. The specific calculation formula is: Initial Warning Threshold = Baseline Value × (1 + ∑(wi × ti) / T), where wi is the standardized weight of the i-th time segment, ti is the duration of the time segment, and T is the total impact time. When a patient takes multiple medications simultaneously, the system will consider the synergistic or antagonistic effects between the drugs and adjust the weight coefficient to reflect the combined impact of the multi-drug combination. This time-interval-based weighted calculation method can more accurately reflect the dynamic impact of drugs on inflammatory markers, making the initial warning threshold more consistent with the patient's actual medication status. For example, a patient with rheumatoid arthritis has a baseline C-reactive protein value of 5 mg / L. After considering the impact of the patient's daily prednisone intake of 10 mg, the initial warning threshold obtained through weighted calculation is 8 mg / L. This threshold fully considers the inhibitory effect of the drugs on this indicator within 24 hours.

[0050] Based on the above embodiment, as an optional embodiment, in step 306: compensating the initial warning threshold set in combination with the vital sign information to obtain the target warning threshold set, this step may also include the following steps: Step 316: For each inflammatory marker, obtain the dosage of each drug within the time interval; calculate the inhibition coefficient of each drug on the inflammatory marker, where the inhibition coefficient is a mapping coefficient between the drug dosage and the change in the inflammatory marker.

[0051] Specifically, to accurately assess the impact of drugs on inflammatory markers, it is necessary to first obtain detailed dosage information for all medications used by the patient during each time period and, based on this information, calculate the drug inhibition coefficient. The system first extracts medication information from the electronic medical order system for each time period, including drug name, dosage, frequency, and route of administration. For example, for patients taking prednisone, the system records their specific medication usage during each time period, such as 10mg of prednisone in the morning and 5mg in the evening. The system then analyzes large-scale clinical data to establish a quantitative relationship model between drug dosage and changes in inflammatory markers. This model uses regression analysis, with drug dosage as the independent variable and changes in inflammatory markers as the dependent variable. Data fitting is used to derive a mapping function between the two. The inhibition coefficient is calculated using a standardized approach: changes in both drug dosage and inflammatory markers are converted into percentages relative to baseline values, and the ratio between the two is then calculated. The calculation formula is: Inhibition coefficient = (ΔM / M0) / (ΔD / D0), where ΔM represents the change in inflammatory markers, M0 represents the baseline value of inflammatory markers, ΔD represents the change in drug dosage, and D0 represents the standard reference dose of the drug. For example, if a patient takes 10 mg of prednisone (standard dose) and their C-reactive protein level decreases from a baseline value of 5 mg / L to 3 mg / L, the inhibition coefficient of prednisone on C-reactive protein can be calculated to be 0.4. This inhibition coefficient, calculated based on actual clinical data, accurately reflects the inhibitory effect of different drugs on inflammatory markers and provides a reliable reference for the calculation of subsequent warning thresholds. When a patient takes multiple medications simultaneously, the system will consider drug interactions and make appropriate adjustments to the inhibition coefficient to reflect the combined effect of the multi-drug combination.

[0052] Step 326: Determine an initial warning threshold corresponding to the inflammatory marker based on the mapping coefficient and the baseline value of the inflammatory marker.

[0053] Specifically, to accurately assess the reasonable fluctuation range of inflammatory markers during drug treatment, it is necessary to calculate the corresponding initial warning threshold based on the aforementioned mapping coefficients and the baseline values ​​of the inflammatory markers. The system first determines the baseline values ​​of each inflammatory marker based on the patient's clinical baseline data. These baseline values ​​reflect the patient's inflammatory index levels when not under the influence of medication. For example, a patient's baseline C-reactive protein value before starting medication is 5 mg / L, and the baseline procalcitonin value is 0.5 ng / mL. The system then takes the inhibitory effects of drugs into account and uses a weighted cumulative approach to assess the combined impact of multiple drugs. The specific calculation formula is as follows: Initial Warning Threshold = Baseline Value × (1-∑(ki × di × wi)), where ki is the inhibition coefficient of the i-th drug, di is the standardized dosage of the drug, and wi is the time weighting factor. The time weighting factor reflects the time-varying characteristics of the drug's effect intensity and is calculated using a pharmacokinetic model. For example, when a patient uses prednisone (inhibition coefficient 0.4, standardized dosage 1.0, time weight 0.8) and methotrexate (inhibition coefficient 0.3, standardized dosage 0.5, time weight 0.6) simultaneously, the system can calculate the initial warning threshold of C-reactive protein to be 3.4 mg / L. This method based on comprehensive calculation of multiple factors not only takes into account the inhibitory effect of a single drug, but also reflects the dynamic characteristics of drug action through time weighting, which can provide more accurate early warning judgment criteria for inflammation monitoring under different medication regimens. The initial warning threshold calculated in this way takes into account the expected therapeutic effect of the drug while retaining sufficient warning sensitivity, and can issue timely warning prompts when abnormal fluctuations occur in inflammatory indicators.

[0054] Step 336: Combine the initial warning thresholds of each inflammatory marker into an initial warning threshold group.

[0055] Specifically, because a single inflammatory marker may not fully reflect a patient's inflammatory status, and different inflammatory markers complement and validate each other, it is necessary to integrate the initial warning thresholds for each inflammatory marker into a comprehensive warning threshold set. The system first establishes a standardized data structure to store and manage warning threshold information for multiple inflammatory markers. This data structure contains attribute fields such as the inflammatory marker type, unit of measurement, and initial warning threshold. For example, for a patient with rheumatoid arthritis taking prednisone and methotrexate, the initial warning threshold set might include thresholds for the following inflammatory indicators: 3.4 mg / L for C-reactive protein, 0.4 ng / mL for procalcitonin, 25 mm / h for erythrocyte sedimentation rate, 9.5 × 10^9 / L for white blood cell count, and 75% for neutrophil ratio. The system organizes this threshold information into an associative array, creating a unified data index to facilitate subsequent warning determination and recall. This combined warning threshold setting enables comprehensive monitoring of a patient's inflammatory status from multiple dimensions, improving the reliability and accuracy of warnings. When any inflammatory marker exceeds its corresponding warning threshold, the system will promptly issue an alert, while also cross-validating changes in other inflammatory markers to avoid misjudgments caused by fluctuations in a single indicator. This multi-indicator collaborative warning mechanism can better adapt to the complex and ever-changing needs of inflammation monitoring in clinical practice, providing more comprehensive and reliable decision-making support for medical staff.

[0056] Step 104: The initial warning threshold value group is compensated in combination with the vital sign information to obtain the target warning threshold value group.

[0057] Among them, the target warning threshold group refers to a set of warning thresholds for inflammatory markers obtained after correction for drug effects and compensation for physical sign information. This set of thresholds includes warning criteria for multiple inflammatory markers, such as C-reactive protein (CRP), procalcitonin (PCT), white blood cell count (WBC), neutrophil ratio (NEU%) and other common inflammatory indicators. Each inflammatory marker has its corresponding target warning threshold, and these thresholds are organized into a complete threshold group for comprehensive assessment of the patient's inflammatory status.

[0058] Specifically, because a patient's vital signs can have an additional impact on the expression of inflammatory markers, and this impact is individual-specific, it is necessary to further refine compensation based on vital sign information, building upon the initial warning thresholds that already account for medication effects. The system first extracts vital sign information from the patient's electronic medical record, including vital sign parameters such as temperature, blood pressure, heart rate, and respiratory rate, as well as basic characteristics such as age, gender, and body mass index. The system then calculates the impact of each vital sign parameter on the inflammatory marker based on a pre-established vital sign-inflammatory marker association model. This association model is constructed using multiple regression analysis, with the vital sign parameters as independent variables and the magnitude of change in the inflammatory marker as the dependent variable. The influence weight coefficients for each parameter are derived through training with large-scale clinical data. To calculate the compensation, the system first normalizes each patient's vital sign parameter to determine the degree of deviation from the normal reference range. The normalized vital sign values ​​are then multiplied by the corresponding weight coefficients to determine the impact factor of each sign on the inflammatory marker. Finally, all influencing factors are weighted and summed to obtain a comprehensive compensation coefficient, which is then multiplied by the initial warning threshold to calculate the final target warning threshold. The compensation calculation formula is: Target Warning Threshold = Initial Warning Threshold × (1 + ∑(αi × δi)), where αi is the weight coefficient for the i-th vital sign parameter, and δi is the standardized deviation value of that vital sign parameter. For example, for a patient with an elevated temperature (38.5°C), the initial warning threshold for C-reactive protein is 8 mg / L. Considering that fever promotes the release of inflammatory factors, the system calculates a temperature compensation coefficient of 1.2, ultimately adjusting the target warning threshold to 9.6 mg / L. This dynamic compensation mechanism based on vital sign information can better adapt to changes in individual patient status, improving the personalization and clinical practicality of warning thresholds.

[0059] It is important to note that the initial correction is performed based on the medication regimen, followed by compensation based on vital signs. This is because the effects of drugs on inflammatory markers are direct and predictable, their mechanisms of action are well-defined, and the extent of the impact can be accurately quantified using pharmacokinetic models. By first considering the effects of medication during correction, baseline values ​​for inflammatory markers can be adjusted to a level that more closely reflects the patient's actual pathological status. For example, glucocorticoids significantly suppress C-reactive protein expression. Failure to first consider the effects of medication during correction may underestimate the patient's actual level of inflammation. While vital signs can also influence the expression of inflammatory markers, their influence is often indirect, complex, and highly variable between individuals. Performing compensation for vital signs in the second step allows for further fine-tuning of warning thresholds, already accounting for the primary effects of medication, to better align with individual patient characteristics. Reversing this order—first considering vital signs for compensation, then performing medication correction—can lead to inaccurate assessments of drug effects, as fluctuations in vital signs may mask or interfere with the actual effects of the medication. Therefore, adopting a sequential approach of first correcting for medication, then correcting for vital signs, more accurately reflects the specific effects of each influencing factor and improves the accuracy and reliability of warning thresholds.

[0060] Based on the above embodiment, as an optional embodiment, in step 104: compensating the initial warning threshold set in combination with the vital sign information to obtain the target warning threshold set, this step may also include the following steps: Step 401: Acquire multiple physical sign reference indicators in the physical sign information, where the physical sign reference indicators include body temperature, blood pressure, heart rate, and blood oxygen saturation; and calculate the deviation rate between each physical sign reference indicator and the corresponding standard physical sign indicator value.

[0061] Specifically, considering that the patient's physical condition can significantly affect the expression of inflammatory markers, the system needs to perform standardized assessments of key physical indicators. During implementation, the system first collects the patient's physical data in real time through medical Internet of Things devices, including body temperature measured by a thermometer, systolic and diastolic blood pressure measured by an electronic blood pressure monitor, heart rate measured by an electrocardiogram monitor, and blood oxygen saturation measured by an oximeter. At the same time, the system retrieves the corresponding standard physical reference values ​​from the medical knowledge base: normal body temperature 37°C, standard blood pressure 120 / 80 mmHg, normal heart rate 60-100 beats / minute, and normal blood oxygen saturation 95-100%. Subsequently, the system uses a standardized calculation method to obtain the deviation rate of each physical indicator. The calculation formula is: Deviation rate = (measured value - standard value) / standard value × 100%. For example, when a patient's temperature is 38.5°C, the temperature deviation rate is (38.5-37°C) / 37 × 100% = 4.1%. When the systolic blood pressure is 150 mmHg, the systolic blood pressure deviation rate is (150-120°C) / 120 × 100% = 25%. Through this standardization process, the system converts vital signs of different dimensions into comparable deviation rates, laying the foundation for subsequent compensation calculations.

[0062] Step 402: Based on the preset physical sign mapping relationship, determine the association weight of each physical sign reference index with different inflammatory markers.

[0063] Specifically, to accurately assess the impact of abnormal physical signs on different inflammatory markers, the system requires a scientific physical sign mapping model. In implementation, the system first uses machine learning methods based on large-scale clinical data analysis to establish a correlation model between physical sign indicators and inflammatory markers. By analyzing the correlation between physical sign changes and inflammatory marker fluctuations in historical case data, the system constructs a multidimensional mapping matrix. Each element in this matrix represents the weight of the impact of a specific physical sign indicator on a specific inflammatory marker, ranging from 0 to 1. For example, based on clinical observations showing a strong correlation between elevated body temperature and elevated C-reactive protein levels, the correlation weight for temperature on C-reactive protein might be set to 0.6. The relatively small impact of temperature on procalcitonin might result in a weight of 0.4. Similarly, abnormal blood pressure might have a weight of 0.3 for C-reactive protein and 0.2 for procalcitonin. This weighting scheme, supported by clinical data, accurately reflects the impact of different physical sign abnormalities on various inflammatory markers, providing a reliable basis for calculating subsequent threshold compensation.

[0064] Step 403: For each inflammatory marker, perform weighted calculation on the deviation rate of each physical sign reference index and the associated weight of the inflammatory marker to obtain a corresponding physical sign compensation coefficient.

[0065] Specifically, to comprehensively assess the impact of multiple vital signs on inflammatory markers, the system requires a weighted calculation to determine the vital sign compensation coefficient. This is done using a weighted accumulation method: the deviation rate of each vital sign reference indicator is multiplied by its corresponding association weight, the sum is then added to the sum, and 1 is added to the sum to obtain the final vital sign compensation coefficient. The calculation formula is: Vital sign compensation coefficient = 1 + ∑(Di × Wi), where Di represents the deviation rate of the i-th vital sign indicator, and Wi represents the association weight of that vital sign indicator with the specific inflammatory marker. For example, for a patient's C-reactive protein index, if the temperature deviation rate is 4.1% (association weight 0.6), the systolic blood pressure deviation rate is 25% (association weight 0.3), the heart rate deviation rate is 30% (association weight 0.2), and the blood oxygen saturation deviation rate is -3% (association weight 0.4), the vital sign compensation coefficient is calculated as: 1 + (4.1% × 0.6 + 25% × 0.3 + 30% × 0.2 - 3% × 0.4) ≈ 1.157. This weighted calculation method not only takes into account the degree of abnormality of various physical signs and indicators, but also reflects the weight of their influence on inflammatory markers, and can obtain a more accurate compensation coefficient.

[0066] Step 404: Multiply the initial warning threshold of each inflammatory marker in the initial warning threshold group by the corresponding physical sign compensation coefficient to obtain the target warning threshold group.

[0067] Specifically, to arrive at a final threshold standard that can be used for clinical early warning, the system multiplies the initial warning threshold by a sign compensation coefficient, thereby incorporating the influence of physical status into the early warning criteria. In practice, for each inflammatory marker in the initial warning threshold set, the system multiplies its initial warning threshold by the corresponding sign compensation coefficient to obtain a target warning threshold after sign compensation. For example, if a patient's C-reactive protein initial warning threshold is 3.4 mg / L and their sign compensation coefficient is 1.157, the final target warning threshold is 3.4 × 1.157 ≈ 3.93 mg / L. Similarly, if the patient's procalcitonin initial warning threshold is 0.4 ng / mL and their sign compensation coefficient is 1.089, the target warning threshold is 0.4 × 1.089 ≈ 0.436 ng / mL. This resulting target warning threshold set encompasses the final warning criteria for all inflammatory markers to be monitored. Each threshold has been corrected for medication effects and compensated for physical status, more accurately reflecting the reasonable fluctuation range of inflammatory indicators under the patient's current condition. When the actual detection value exceeds these target warning thresholds, the system will issue a warning prompt in a timely manner to provide medical staff with reliable clinical decision support.

[0068] Step 105: Collect the current inflammatory marker detection value of the target patient and compare the inflammatory marker detection value with the target warning threshold group. When any indicator in the inflammatory marker detection value is greater than or equal to the corresponding indicator threshold in the target warning threshold group, chronic disease risk warning information for the target patient is generated.

[0069] Among them, the detection value of inflammatory markers refers to the specific numerical indicators obtained through medical testing equipment that reflect the patient's current inflammatory status.

[0070] Among them, the chronic disease risk warning information refers to the comparison result of the target patient's inflammatory marker test value and the target warning threshold group. When any inflammatory marker test value reaches or exceeds the corresponding target warning threshold, the system automatically generates a prompt information reflecting the abnormal inflammatory state of the patient. In the embodiment of the present application, it can be understood as a comprehensive risk assessment information including the name of the abnormal inflammatory marker, the current test value, the target warning threshold, the degree of exceeding the threshold, key physical parameters and clinical medication status. For example, when the patient's C-reactive protein is detected to be 4.2mg / L, exceeding the target warning threshold of 3.93mg / L, the warning information generated by the system will include "C-reactive protein test value 4.2mg / L, exceeding the target warning threshold by 6.9%, current body temperature 38.5℃, timely clinical intervention is recommended" and other content. This warning information is used to promptly remind medical staff that the patient is at risk of abnormal inflammatory state, and provide a decision-making basis for the clinic to adjust the treatment plan in time and prevent acute attacks and complications of chronic diseases, thereby achieving precise management and early intervention of chronic disease patients.

[0071] Specifically, to achieve real-time monitoring and early warning of chronic disease risks in target patients, the system requires dynamic tracking and threshold comparison of patients' inflammatory markers. The system obtains real-time inflammatory marker test results from the hospital's laboratory information system (LIS), including but not limited to C-reactive protein, procalcitonin, erythrocyte sedimentation rate, white blood cell count, and neutrophil ratio. These test values ​​are transmitted to the monitoring system via a standardized data interface and automatically compared with previously calculated target early warning thresholds. In implementation, the system uses a parallel comparison algorithm to simultaneously evaluate the test values ​​of multiple inflammatory markers. For example, if a patient's test results show a C-reactive protein level of 4.2 mg / L (target early warning threshold of 3.93 mg / L), a procalcitonin level of 0.42 ng / mL (target early warning threshold of 0.436 ng / mL), and a white blood cell count of 11.2 × 10^9 / L (target early warning threshold of 10.5 × 10^9 / L), the system detects that both the C-reactive protein and white blood cell count have exceeded their respective target early warning thresholds. At this point, the system immediately generates chronic disease risk warning information containing abnormal indicator information. The warning information includes the name of the abnormal indicator, the test value, the degree of exceeding the threshold, and other relevant clinical reference information. The warning information is pushed to the workstations and mobile terminals of relevant medical staff through the hospital information system, and is also recorded in the patient's electronic medical record. This early warning mechanism based on multi-indicator joint monitoring can promptly detect abnormal changes in the patient's inflammatory state, provide medical staff with a decision-making basis for early intervention, and effectively prevent the occurrence of acute attacks and complications of chronic diseases. In this way, the system realizes precise and individualized management of patients with chronic diseases, significantly improving the efficiency and quality of chronic disease prevention and control.

[0072] Reference Figure 2 , a chronic disease risk warning system based on inflammatory markers provided in an embodiment of the present application, the system includes: an information acquisition module, a threshold group determination module, a threshold group compensation module, and a risk warning module, wherein: The information acquisition module is used to obtain the case information and physical sign information of the target patient, including historical inflammatory marker detection records, types of chronic diseases, and medication plans; The threshold group determination module is used to calculate the baseline values ​​of multiple inflammatory markers corresponding to the target patient based on historical inflammatory marker detection records; based on the type of chronic disease, the inflammatory marker combination of the target patient is screened out from each inflammatory marker, and the baseline value of each inflammatory marker in the inflammatory marker combination is corrected based on the medication regimen to obtain the initial warning threshold group; The threshold group compensation module is used to compensate the initial warning threshold group based on the vital sign information to obtain the target warning threshold group; The risk warning module is used to collect the current inflammatory marker detection values ​​of the target patient and compare the inflammatory marker detection values ​​with the target warning threshold group. When any indicator in the inflammatory marker detection value is greater than or equal to the corresponding indicator threshold in the target warning threshold group, chronic disease risk warning information is generated for the target patient.

[0073] Based on the above embodiment, the threshold group determination module is also used to divide the historical inflammatory marker detection records into detection sequences corresponding to multiple preset disease stages, and the preset disease stages include stable period, relapse period and remission period; calculate the mean of the inflammatory marker detection values ​​in the detection sequence corresponding to each disease stage, and obtain the stage characteristic value of the corresponding disease stage; obtain the current disease stage and the most recent relapse time of the target patient; determine the corresponding stage characteristic value based on the current disease stage, and determine the correction coefficient according to the interval from the most recent relapse time; multiply the stage characteristic value by the correction coefficient to obtain the baseline value of each inflammatory marker.

[0074] Based on the above embodiment, the threshold group determination module is also used to obtain a standard inflammatory marker combination template and a medication list for a target patient. The standard inflammatory marker combination template includes inflammatory marker combinations corresponding to multiple types of chronic diseases. In the standard inflammatory marker combination template, the first inflammatory marker corresponding to the type of chronic disease of the target patient is screened out, and based on the type of action of each drug in the medication list, the second inflammatory marker of the target patient is determined. The first inflammatory marker and the second inflammatory marker are used as the inflammatory marker combination for the target patient.

[0075] Based on the above embodiments, the threshold group determination module is also used to extract the dosage and administration time of each type of drug from the medication plan; based on the dosage and administration time of each drug, calculate the drug dosage curve corresponding to each drug; determine the time interval in which each inflammatory marker is affected by the drug according to the drug dosage curve; and combine the time interval in which each inflammatory marker is affected by the drug to perform weighted calculation on the baseline value of each inflammatory marker to obtain the initial warning threshold group.

[0076] Based on the above embodiment, the threshold group determination module is also used to obtain the peak time point of the drug usage curve; calculate the time interval between adjacent peak time points; use the midpoint of each time interval as the dividing point of the time interval; and divide the drug usage curve into multiple time intervals based on each dividing point.

[0077] Based on the above embodiment, the threshold group determination module is also used to obtain the drug dosage of each drug within the time interval for each inflammatory marker; calculate the inhibition coefficient of each drug on the inflammatory marker, the inhibition coefficient is the mapping coefficient between the drug dosage and the change in the inflammatory marker; based on the mapping coefficient and the baseline value of the inflammatory marker, determine the initial warning threshold corresponding to the inflammatory marker; and merge the initial warning threshold of each inflammatory marker into an initial warning threshold group.

[0078] On the basis of the above embodiment, the threshold group compensation module is also used to obtain multiple vital sign reference indicators in the vital sign information, the vital sign reference indicators including body temperature, blood pressure, heart rate and blood oxygen saturation; respectively calculate the deviation rate between each vital sign reference indicator and the corresponding standard vital sign indicator value; based on the preset vital sign mapping relationship, determine the association weight of each vital sign reference indicator to different inflammatory markers; for each inflammatory marker, perform weighted calculation on the deviation rate of each vital sign reference indicator and the association weight of the inflammatory marker to obtain the corresponding vital sign compensation coefficient; multiply the initial warning threshold of each inflammatory marker in the initial warning threshold group by the corresponding vital sign compensation coefficient to obtain the target warning threshold group.

[0079] It should be noted that the above embodiments provide devices that implement their functions using only the division of the above functional modules as examples. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiments are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0080] This application also discloses an electronic device. Figure 3 , Figure 3 The electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0081] The communication bus 302 is used to implement the connection and communication between these components.

[0082] The user interface 303 may include a display interface and a camera interface. Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0083] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0084] The processor 301 may include one or more processing cores. Using various interfaces and circuits, the processor 301 connects to various components within the server. It executes instructions, programs, code sets, or instruction sets stored in the memory 305, as well as accesses data stored in the memory 305, to perform various server functions and process data. Optionally, the processor 301 may be implemented using at least one of the following hardware forms: a digital signal processing (DSP), a field-programmable gate array (FPGA), or a programmable logic array (PLA). The processor 301 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily processes the operating system, user interface graphics, and application programs; the GPU is responsible for rendering and drawing content displayed on the display screen; and the modem handles wireless communications. It is understood that the modem may also be implemented as a separate chip, rather than integrated into the processor 301.

[0085] Among them, the memory 305 may include a random access memory (RAM) or a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may also optionally be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 , as a computer storage medium, the memory 305 may include an operating system, a network communication module, a user interface module, and an application program for a chronic disease risk early warning method based on inflammatory markers.

[0086] exist Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the memory 305 to store an application program for a chronic disease risk warning method based on inflammatory markers. When executed by one or more processors 301, the electronic device 300 executes one or more methods in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should know that this application is not limited to the described order of actions, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for this application.

[0087] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0088] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely schematic, such as the division of units, which is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interface, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0089] Units described as separate components may or may not be physically separate, and 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 these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0090] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0091] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of this application, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the method of this application. The aforementioned memory includes various media that can store program code, such as USB flash drives, mobile hard drives, magnetic disks, or optical disks.

[0092] The above are merely exemplary embodiments of the present disclosure and are not intended to limit the scope of the present disclosure. In other words, any equivalent variations and modifications made in accordance with the teachings of the present disclosure are still within the scope of the present disclosure. Those skilled in the art will readily conceive of other embodiments of the present disclosure after considering the disclosure in this specification and practice.

[0093] This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not described in this disclosure. The description and examples are to be considered as illustrative only.

Claims

1. A chronic disease risk early warning method based on inflammatory markers, characterized in that: include: Obtaining medical records and physical signs of target patients, including historical inflammatory marker test records, types of chronic diseases, and medication regimens; Calculating the baseline values ​​of multiple inflammatory markers corresponding to the target patient based on the historical inflammatory marker detection records; Based on the type of chronic disease, the target patient's inflammatory marker combination is screened out from each of the inflammatory markers, and the baseline value of each inflammatory marker in the inflammatory marker combination is corrected based on the medication regimen to obtain an initial warning threshold value group; Compensating the initial warning threshold value group in combination with the vital sign information to obtain a target warning threshold value group; The current inflammatory marker detection value of the target patient is collected, and the inflammatory marker detection value is compared with the target warning threshold group. When any indicator in the inflammatory marker detection value is greater than or equal to the corresponding indicator threshold in the target warning threshold group, chronic disease risk warning information of the target patient is generated.

2. The chronic disease risk early warning method based on inflammatory markers according to claim 1, characterized in that: The step of calculating the baseline values ​​of the target patient corresponding to the plurality of inflammatory markers based on the historical inflammatory marker detection records includes: Dividing the historical inflammatory marker detection records into detection sequences corresponding to a plurality of preset disease course stages, wherein the preset disease course stages include a stable stage, a relapse stage, and a remission stage; Calculating the mean of the inflammatory marker detection values ​​in the detection sequence corresponding to each of the disease course stages to obtain the stage characteristic value of the corresponding disease course stage; Obtaining the current disease stage and most recent relapse time of the target patient; Determining a corresponding stage characteristic value based on the current disease stage, and determining a correction coefficient based on the interval from the most recent relapse time; The stage characteristic value is multiplied by the correction coefficient to obtain the baseline value of each inflammatory marker.

3. The chronic disease risk early warning method based on inflammatory markers according to claim 1, characterized in that: The method of screening out the target patient's inflammatory marker combination from among the inflammatory markers based on the type of chronic disease includes: Obtaining a standard inflammatory marker combination template and a medication list for the target patient, wherein the standard inflammatory marker combination template includes inflammatory marker combinations corresponding to multiple types of chronic diseases; In the standard inflammatory marker combination template, the first inflammatory marker corresponding to the chronic disease type of the target patient is screened out, and based on the action type of each drug in the medication list, the second inflammatory marker of the target patient is determined; The first inflammatory marker and the second inflammatory marker are used as an inflammatory marker combination of the target patient.

4. The chronic disease risk early warning method based on inflammatory markers according to claim 1, characterized in that: The baseline value of each inflammatory marker in the inflammatory marker combination is corrected based on the medication regimen to obtain an initial warning threshold value group, including: Extracting the dosage and administration time of each drug from the medication regimen; Calculating a drug dosage curve corresponding to each drug based on the dosage and administration time of each drug; determining the time interval during which each inflammatory marker is affected by the drug according to the drug dosage curve; Combined with the time interval during which each of the inflammatory markers is affected by the drug, the baseline value of each of the inflammatory markers is weighted and calculated to obtain an initial warning threshold value group.

5. The chronic disease risk early warning method based on inflammatory markers according to claim 4, characterized in that: Determining the time interval during which each inflammatory marker is affected by the drug according to the drug dosage curve includes: Obtaining the peak time point of the drug dosage curve; Calculate the time interval between adjacent peak moments; The midpoint of each time interval is used as the dividing point of the time interval; The drug dosage curve is divided into multiple time intervals based on each of the dividing points.

6. The chronic disease risk early warning method based on inflammatory markers according to claim 4, characterized in that: The initial warning threshold value group is obtained by weighted calculation of the baseline value of each inflammatory marker based on the time interval during which each inflammatory marker is affected by the drug, including: For each of the inflammatory markers, obtaining the dosage of each drug within the time interval; Calculating the inhibition coefficient of each drug on the inflammatory marker, where the inhibition coefficient is a mapping coefficient between the drug dosage and the change in the inflammatory marker; determining an initial warning threshold corresponding to the inflammatory marker based on the mapping coefficient and the baseline value of the inflammatory marker; The initial warning thresholds of the inflammatory markers are combined into an initial warning threshold group.

7. The chronic disease risk early warning method based on inflammatory markers according to claim 1, characterized in that: The compensating the initial warning threshold value group in combination with the vital sign information to obtain a target warning threshold value group includes: Acquiring multiple physical sign reference indicators from the physical sign information, wherein the physical sign reference indicators include body temperature, blood pressure, heart rate, and blood oxygen saturation; Calculating the deviation rate between each reference physical sign index and the corresponding standard physical sign index value respectively; Based on the preset physical sign mapping relationship, determining the association weight of each physical sign reference index with different inflammatory markers; For each of the inflammatory markers, weighted calculation is performed on the deviation rate of each of the physical sign reference indicators and the associated weight of the inflammatory marker to obtain a corresponding physical sign compensation coefficient; The initial warning threshold value of each inflammatory marker in the initial warning threshold value group is multiplied by the corresponding physical sign compensation coefficient to obtain the target warning threshold value group.

8. A chronic disease risk early warning system based on inflammatory markers, characterized by: The system comprises: An information acquisition module is used to obtain case information and physical sign information of the target patient, including historical inflammatory marker detection records, types of chronic diseases, and medication regimens; a threshold group determination module, configured to calculate the baseline values ​​of multiple inflammatory markers corresponding to the target patient based on the historical inflammatory marker detection records; screen out the inflammatory marker combination of the target patient from each of the inflammatory markers based on the type of chronic disease; and correct the baseline value of each inflammatory marker in the inflammatory marker combination based on the medication regimen to obtain an initial warning threshold group; A threshold group compensation module, configured to compensate the initial warning threshold group in combination with the vital sign information to obtain a target warning threshold group; The risk warning module is used to collect the current inflammatory marker detection value of the target patient and compare the inflammatory marker detection value with the target warning threshold group. When any indicator in the inflammatory marker detection value is greater than or equal to the corresponding indicator threshold in the target warning threshold group, chronic disease risk warning information of the target patient is generated.

9. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the chronic disease risk warning method based on inflammatory markers as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, and when the instructions are executed, the chronic disease risk early warning method based on inflammatory markers according to any one of claims 1 to 7 is executed.

Images