A method for predicting gout attack risk based on joint prediction

Abstract

This invention relates to the field of disease prediction technology and discloses a method for predicting gout attack risk based on joint prediction. The method includes step one: acquiring biological sample detection data of the subject, wherein the biological sample detection data includes at least serum uric acid concentration data; and step two: based on the peripheral blood cell count data, neutrophil count, monocyte count, and lymphocyte count. This method for predicting gout attack risk based on joint prediction constructs a metabolic and immune dual-dimensional prediction model by jointly applying serum uric acid, representing metabolic burden, and a systemic immune inflammatory index, representing systemic inflammatory status. Validated by a large-sample prospective cohort study, the dual-indicator joint prediction significantly improves both the sensitivity and specificity compared to a single serum uric acid index, effectively overcoming the shortcomings of a single uric acid index in failing to identify patients with gout attacks at normal uric acid levels and in over-predicting asymptomatic hyperuricemia patients.

Description

Technical Field

[0001] This invention relates to the field of pain prediction technology, and in particular to a method for predicting the risk of gout attacks based on joint prediction. Background Technology

[0002] Gout is a metabolic autoinflammatory disease caused by purine metabolism disorder, which leads to abnormally high blood uric acid levels, resulting in the deposition of urate crystals and activation of the innate immune system. Its clinical features are redness, swelling, heat and pain in the affected joints, recurrent acute attacks, and persistent symptoms. Long-term recurrent attacks can lead to joint deformities, urate nephropathy and even renal failure. It is also often accompanied by serious complications such as hypertension, cardiovascular disease and metabolic syndrome, which seriously affect the quality of life of patients and place a heavy burden on the clinical diagnosis and treatment system.

[0003] Early warning of acute gout attacks and precise stratification of high-risk groups are the core links in clinical practice to achieve preventive intervention for gout, reduce the frequency of attacks, and improve the long-term prognosis of patients. Precise and efficient predictive indicators and standardized assessment methods are the key technical support for achieving this goal.

[0004] Clinical evidence in rheumatology reveals that gout attacks are not driven by a single factor, but rather by the combined effects of urate crystal deposition and NLRP3 inflammasome-mediated innate immune activation. While serum uric acid has long been considered the core metabolic basis of gout, clinical studies have repeatedly confirmed that hyperuricemia is only a necessary, not sufficient, condition for gout attacks: up to 15% of acute gout patients have normal serum uric acid levels during an attack, and a large number of individuals with chronic hyperuricemia never experience a clinical gout attack throughout their lives. This phenomenon strongly suggests that, in addition to uric acid metabolic load, systemic inflammatory states play a significant independent regulatory role in the risk of gout attacks.

[0005] Currently, the assessment and prediction of the risk of acute gout attacks mainly rely on the following existing technologies:

[0006] 1. Assessment using a single serum uric acid index

[0007] In clinical practice, serum uric acid levels are generally used as the main basis for judging the condition of gout, setting uric acid-lowering treatment goals, and roughly assessing the likelihood of an attack. It is currently the most widely used risk assessment method.

[0008] 2. Single inflammatory marker-assisted assessment

[0009] Some studies have attempted to use single inflammatory markers such as neutrophil / lymphocyte ratio (NLR) and C-reactive protein (CRP) to evaluate the degree of local or systemic inflammation in gout patients, but most of these studies are limited to cross-sectional correlation analysis and are rarely used for prospective prediction of long-term attack risk.

[0010] 3. Univariate statistical analysis

[0011] Current risk assessments mostly employ traditional univariate statistical analysis methods, without systematically correcting for confounding factors such as age, body mass index (BMI), blood lipid levels, liver and kidney function, and comorbidities. They also lack standardized multivariate correction models, resulting in insufficient accuracy and reliability of prediction results.

[0012] 4. Lack of universally accepted thresholds and standardized stratification criteria

[0013] Regarding the optimal cutoff values ​​for serum uric acid and various inflammatory indices to predict gout attacks, existing studies have not yet established a unified standard validated by large-sample prospective cohort follow-ups. In clinical applications, grouping methods are inconsistent, making it difficult to compare and replicate research results across different studies.

[0014] 5. No dual-indicator joint forecasting system

[0015] Existing technologies all rely on the independent use of single metabolic or inflammatory indicators, and have not yet established a dual-dimensional joint assessment model of "uric acid metabolic load + systemic immune inflammation level," nor have they elucidated the synergistic predictive effect of the two, thus failing to achieve accurate identification of high-risk groups. Summary of the Invention

[0016] Given the shortcomings of existing technologies, such as poor accuracy and high false negative rate in predicting gout using a single serum uric acid index, inability to effectively distinguish between truly high-risk individuals and asymptomatic hyperuricemia patients; failure to consider systemic inflammatory status, thus failing to reflect the pathological nature of gout attacks driven by both metabolic and immune mechanisms, resulting in low predictive efficacy; lack of standardized cutoff values ​​established by prospective studies, leading to poor clinical operability; failure to exclude interference from multiple confounding factors, resulting in insufficient stability of prediction results; and lack of a combined stratification scheme, making it difficult to accurately identify ultra-high-risk patient groups with "high metabolic load + high inflammatory state," and thus failing to meet the clinical needs for individualized and precise stratified management, this invention is proposed.

[0017] Therefore, the purpose of this invention is to provide a method for predicting gout attack risk based on joint analysis. The method involves combining serum uric acid, representing metabolic burden, with a systemic immune inflammatory index, representing systemic inflammatory status, to construct a dual-dimensional prediction model of "metabolism + immunity." Large-scale prospective cohort studies have validated that the combined prediction of these two indicators significantly improves both the sensitivity and specificity compared to using serum uric acid as a single indicator.

[0018] To address the aforementioned technical problems, this invention provides the following technical solution: a method for predicting gout attack risk based on joint prediction, comprising the following steps:

[0019] Step 1: Obtain biological sample test data from the subject. The biological sample test data includes at least serum uric acid concentration data and peripheral blood cell count data used to calculate the systemic immune inflammation index (SIRI).

[0020] Step 2: Based on the neutrophil count, monocyte count, and lymphocyte count in the peripheral blood cell count data, calculate the subject's systemic immune inflammation index (SIRI). The calculation formula is: SIRI = neutrophil count × monocyte count / lymphocyte count.

[0021] Step 3: Compare the subject's serum uric acid concentration with a preset serum uric acid threshold, and compare the subject's SIRI value with a preset SIRI threshold.

[0022] Step 4: Based on the comparison results, the subjects are divided into different risk groups. Subjects whose serum uric acid concentration is higher than the serum uric acid threshold and whose SIRI is higher than the SIRI threshold are divided into the high risk group for gout attacks.

[0023] As a preferred embodiment of the method for predicting gout attack risk based on joint prediction according to the present invention, wherein: the preset serum uric acid threshold value in step three is the median serum uric acid value of the population cohort to which the subject belongs; the preset SIRI threshold value is the median SIRI value of the population cohort to which the subject belongs.

[0024] As a preferred embodiment of the method for predicting gout attack risk based on joint prediction as described in this invention, the different risk groups in step four specifically include:

[0025] Low serum uric acid combined with low SIRI group;

[0026] Low serum uric acid combined with high SIRI group;

[0027] High serum uric acid combined with low SIRI group; and

[0028] The group with high serum uric acid and high SIRI was classified as the high risk group for gout attacks.

[0029] As a preferred embodiment of the method for predicting the risk of gout attacks based on joint prediction as described in this invention, the method further includes: using the low serum uric acid combined with low SIRI group as a reference group, calculating the risk ratio (HR) of gout attacks for the remaining groups using a multivariate Cox proportional hazards regression model, so as to quantitatively assess the relative risk of gout attacks for each group of subjects.

[0030] As a preferred embodiment of the method for predicting the risk of gout attacks based on joint prediction as described in this invention, the multivariate Cox proportional hazards regression model is a model that is stepwise adjusted for confounding factors, which include one or more of the following: age, family history of gout, disease duration, tophi, systolic blood pressure, diastolic blood pressure, body mass index, triglycerides, total cholesterol, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, fasting blood glucose, estimated glomerular filtration rate, and C-reactive protein.

[0031] As a preferred embodiment of the method for predicting gout attack risk based on joint prediction according to the present invention, the subject is a male gout patient; the gout attack risk includes the risk of acute gout attack and / or the risk of frequent gout attacks.

[0032] As a preferred embodiment of the method for predicting gout attack risk based on joint prediction according to the present invention, wherein: the biological sample test data of the subject in step one is the baseline test data of the subject before receiving uric acid-lowering treatment.

[0033] As a preferred embodiment of the method for predicting gout attack risk based on joint prediction according to the present invention, the method further includes: using a restricted cubic spline model to assess the dose-response relationship between serum uric acid concentration and / or SIRI and gout attack risk.

[0034] As a preferred embodiment of the method for predicting gout attack risk based on joint prediction according to the present invention, an apparatus for predicting gout attack risk based on joint prediction is characterized by comprising:

[0035] The data acquisition module is used to acquire biological sample test data of the subject, which includes at least serum uric acid concentration data and peripheral blood cell count data for calculating the systemic immune inflammation index (SIRI).

[0036] The index calculation module is used to calculate the subject's systemic immune inflammation index (SIRI) based on the neutrophil count, monocyte count and lymphocyte count in the peripheral blood cell count data. The calculation formula is: SIRI = neutrophil count × monocyte count / lymphocyte count.

[0037] The comparison module is used to compare the subject's serum uric acid concentration value with a preset serum uric acid threshold value, and to compare the subject's SIRI value with the preset SIRI threshold value.

[0038] The stratification module is used to divide the subjects into different risk groups based on the comparison results. Subjects whose serum uric acid concentration is higher than the serum uric acid threshold and whose SIRI is higher than the SIRI threshold are classified as the high risk group for gout attacks.

[0039] Compared with the prior art, the present invention has at least the following beneficial effects:

[0040] 1. This invention combines serum uric acid, which represents metabolic load, with the systemic immune inflammatory index, which represents systemic inflammatory status, to construct a dual-dimensional prediction model of metabolism and immunity. Validated by a large-sample prospective cohort study, the combined prediction of the two indicators significantly improves both the sensitivity and specificity compared to a single serum uric acid indicator. This effectively overcomes the shortcomings of a single uric acid indicator in failing to identify patients with normal uric acid levels experiencing an attack and in over-predicting asymptomatic hyperuricemia patients.

[0041] 2. This invention reveals the synergistic amplification effect of serum uric acid (UA) representing metabolic load and systemic inflammatory state (SIRI) through a four-group method. The hazard ratio (HR) for acute gout attacks in the high UA combined with high SIRI group reached 2.240, and the HR for frequent attacks reached 1.709, which were significantly higher than those in any single-indicator elevated group. This finding fills the gap in the existing technology for the lack of joint predictive indicators, enabling clinicians to accurately identify a subgroup of extremely high-risk patients who simultaneously possess the dual risk characteristics of high metabolic load and high inflammatory state.

[0042] 3. This invention, through a large-sample, rigorously screened prospective cohort study of male gout patients and a complete 24-week standardized follow-up, determined the clinical cutoff values ​​for serum uric acid and SIRI using the median method. These cutoff values ​​have been validated through standardized research, with uniform grouping criteria, ensuring reproducibility and comparability. They can be directly converted into routine clinical testing items without requiring additional complex equipment, making them highly practical. Furthermore, restricted cubic spline analysis clearly confirmed that both serum uric acid and SIRI exhibit a linear dose-response relationship with the risk of gout attacks, without significant non-linear threshold effects. This facilitates real-time dynamic monitoring and risk reassessment of changes in these indicators at different levels in clinical practice.

[0043] 4. This invention constructs a multivariate Cox proportional hazards regression model with three stepwise adjustments for confounding factors, systematically excluding multiple interfering factors such as age, disease duration, comorbidities, blood lipids, and renal function, ensuring the stability and reliability of the prediction results. This multi-level statistical analysis method is standardized and rigorous, providing high-quality evidence-based support for clinical decision-making. Furthermore, through dual-indicator stratification, clinicians can implement targeted early intensive uric acid-lowering treatment and anti-inflammatory interventions for identified high-risk patients, effectively reducing the incidence of acute and frequent gout attacks and minimizing long-term complications. This provides objective, quantitative, and dynamically monitorable technical support for the stratified clinical management of gout. Attached Figure Description

[0044] Figure 1 This is a flowchart illustrating the steps of the method for predicting gout attack risk based on joint prediction according to the present invention. Detailed Implementation

[0045] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0046] Reference Figure 1 This invention provides a method for predicting the risk of gout attacks based on a combination of serum uric acid and systemic immune inflammatory indices. The theoretical basis of this method is that gout attacks are not driven by a single metabolic factor, but rather by the combined effects of urate crystal deposition and innate immune inflammatory activation. Serum uric acid represents the metabolic load dimension, while the systemic immune inflammatory index represents the systemic inflammatory state dimension. Combining the two allows for a comprehensive assessment of gout attack risk from both metabolic and immune dimensions, overcoming the limitations of traditional single uric acid indicators in predicting gout attack efficacy.

[0047] The formula for calculating the systemic immune inflammatory index (SIRI) is: SIRI = Neutrophil count × Monocyte count / Lymphocyte count. The peripheral blood cell count data required for this formula can be obtained through routine blood tests, which are convenient and inexpensive to obtain clinically.

[0048] Study subject selection and cohort establishment

[0049] Step 1: Subject Screening

[0050] First, based on internationally recognized classification criteria for gout, male patients meeting the diagnostic criteria were selected from the target population, with the age range limited to 18 to 75 years. To ensure the homogeneity of the study subjects and the reliability of the analysis results, strict exclusion criteria were established:

[0051] (1) Exclude patients with baseline serum uric acid levels below 7 mg / dL to focus on individuals with confirmed hyperuricemia;

[0052] (2) Exclude patients who are in the acute phase of gout attack in order to avoid interference with baseline indicators by acute inflammatory state;

[0053] (3) Exclude patients who cannot or refuse to undergo a 2-week drug washout and low-purine diet washout period to ensure the stability of their metabolic status before treatment;

[0054] (4) Exclude patients with an estimated glomerular filtration rate of less than 60 mL / min / 1.73 m² to control the impact of severe renal insufficiency on uric acid metabolism and subsequent selection of uric acid-lowering drugs;

[0055] (5) Exclude patients with alanine aminotransferase or aspartate aminotransferase levels higher than 80 U / L to avoid significant liver dysfunction.

[0056] (6) Exclude patients with serious comorbidities such as malignant tumors, brain tumors, kidney tumors, cerebral infarction or myocardial infarction.

[0057] Based on the above screening criteria, a total of 584 gout patients were ultimately included in the prospective cohort study.

[0058] Step Two: Study Design and Standardized Treatment

[0059] All participants enrolled in the study signed written informed consent forms. The study protocol has been reviewed and approved by the ethics committee and registered with the clinical trial registry, strictly adhering to the ethical guidelines of the Declaration of Helsinki.

[0060] The study employed a standard uric acid-lowering treatment regimen: all subjects initially received febuxostat 20 mg / day. A regular follow-up schedule was established, with outpatient follow-ups every 4 weeks. At the 4-week follow-up after the initial medication, serum uric acid levels were measured. If the level remained above 6 mg / dL, the febuxostat dose was adjusted to 40 mg / day and maintained at this dose until the end of the study period.

[0061] Step 3: Follow-up and Outcome Recording

[0062] Throughout the 24-week follow-up period, any acute gout attacks were closely monitored and recorded. If an acute attack occurred during the follow-up period, colchicine or nonsteroidal anti-inflammatory drugs (NSAIDs) were administered for symptomatic treatment according to clinical guidelines. Drug safety was continuously monitored, and if a subject's serum transaminase levels exceeded twice the upper limit of normal, appropriate hepatoprotective drugs were administered.

[0063] During the study, 20 participants withdrew due to reasons such as self-discontinuation of medication or loss to follow-up. Ultimately, 524 participants completed the entire 24-week follow-up, and their complete data were used for the final statistical analysis.

[0064] The outcome of an acute gout attack was defined as: swelling and pain in at least one joint during the follow-up period, with a visual analog scale score greater than 3; or the subject taking a nonsteroidal anti-inflammatory drug or colchicine due to joint swelling and pain. Frequent attacks were defined as two or more acute attacks occurring during a 24-week follow-up period.

[0065] Baseline data and variable system acquisition

[0066] Comprehensive data collection was conducted before subjects began uric acid-lowering treatment (i.e., at baseline). The data collected specifically included:

[0067] (I) Demographic and Clinical Characteristics

[0068] This includes: age, height, weight, systolic blood pressure, diastolic blood pressure, age of onset of gout, course of disease, family history of gout, smoking history, drinking history, frequency of previous gout attacks, and presence of tophi.

[0069] Body mass index (BMI) is calculated based on height and weight. The formula is: BMI = weight (kg) / height (m)².

[0070] (ii) Comorbidities

[0071] Based on medical history records or current treatment status, record whether there are any complications such as hypertension, cardiovascular disease, fatty liver, hyperlipidemia, diabetes, or kidney stones.

[0072] (III) Laboratory Indicators

[0073] At baseline and at each subsequent follow-up visit, the following parameters were measured: serum uric acid, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, fasting blood glucose, triglycerides, total cholesterol, alanine aminotransferase, aspartate aminotransferase, blood urea nitrogen, and creatinine.

[0074] Additional measurements at baseline include: 24-hour urinary uric acid excretion, uric acid excretion fraction, and the ratio of urinary microalbumin to urinary creatinine.

[0075] (iv) Renal function assessment

[0076] A specific formula is used to calculate and estimate the glomerular filtration rate to assess kidney function. The specific formula is as follows:

[0077] When creatinine (Cr) ≤ 0.9 mg / dL, eGFR = 142 × (Cr / 0.9)⁻ 0 ·³ 0 ²×(0.9938)^age;

[0078] When creatinine (Cr) > 0.9 mg / dL, eGFR = 142 × (Cr / 0.9)⁻¹·² 00 ×(0.9938)^age

[0079] (v) Peripheral blood cell count data

[0080] Peripheral blood samples were collected at baseline for complete blood cell count testing to obtain key data such as neutrophil count, lymphocyte count, monocyte count, and platelet count.

[0081] Calculation of core inflammatory markers

[0082] Based on baseline peripheral blood cell count data, a series of inflammation-related biomarkers were calculated. The calculation formulas for each indicator are as follows:

[0083] 1. Neutrophil to Lymphocyte Ratio (NLR)

[0084] NLR = Neutrophil count / Lymphocyte count

[0085] 2. Systemic Immune Inflammatory Index (SII)

[0086] SII = Platelet count × Neutrophil count / Lymphocyte count

[0087] 3. Systemic Immune Inflammatory Index (SIRI)

[0088] SIRI = Neutrophil count × Monocyte count / Lymphocyte count

[0089] 4. Inflammatory Prognostic Index (IPI)

[0090] IPI = C-reactive protein × NLR / albumin

[0091] Among them, the Systemic Immune Inflammatory Index (SIRI) is the core inflammation prediction indicator of this invention.

[0092] V. Statistical Modeling and Risk Association Analysis

[0093] All statistical analyses were performed using SPSS 27.0 and R software (version 4.5.1). Hypothesis testing was performed using a two-tailed test, and a p-value less than 0.05 was considered statistically significant.

[0094] Step 1: Baseline Feature Description and Group Comparison

[0095] First, the participants were stratified based on the median values ​​of serum uric acid and systemic immune inflammatory indices, and the baseline characteristics of each stratum were described. Continuous variables were expressed as mean ± standard error, and categorical variables were expressed as frequency (percentage). For inter-group comparisons, the Kruskal-Wallis rank-sum test was used for continuous variables, and the chi-square test was used for categorical variables.

[0096] Step 2: Survival Curve Analysis

[0097] The Kaplan-Meier method was used to plot the gout attack-free survival curves of subjects in different serum uric acid level groups and different SIRI level groups, and the log-rank test was used to preliminarily compare the differences in gout attack-free survival probability among the groups.

[0098] Step 3: Construction of a multivariate Cox proportional hazards regression model

[0099] To further assess the independent and combined associations between serum uric acid and SIRI with the risk of gout attacks, a multivariate Cox proportional hazards regression model was constructed with three stepwise adjustments for confounding factors:

[0100] Model 1: Only adjusts for two basic demographic and genetic factors: age and family history.

[0101] Model 2: Based on Model 1, further adjustments are made for disease course, tophi, systolic blood pressure, diastolic blood pressure, and body mass index to control the impact of disease severity and baseline physiological state.

[0102] Model 3: Based on Model 2, further corrections are made for triglycerides, total cholesterol, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, fasting blood glucose, estimated glomerular filtration rate, and C-reactive protein to comprehensively control the confounding effects of metabolic state, renal function, and acute inflammatory response.

[0103] By gradually constructing these three models, we can clearly demonstrate the hazard ratios (HRs) and 95% confidence intervals of serum uric acid and SIRI after controlling for different degrees and dimensions of confounding factors, so as to assess the strength of their independent association with the risk of gout attacks.

[0104] Step 4: Dose-Response Analysis

[0105] This study uses a restricted cubic spline model to explore whether a nonlinear dose-response relationship exists between serum uric acid, SIRI, and the risk of gout attacks. This analysis is achieved by incorporating restricted cubic spline terms into the aforementioned multivariate Cox regression model, which visually displays the trend of hazard ratio changes with serum uric acid or SIRI levels across the entire range of index values.

[0106] Risk stratification and joint effect verification

[0107] Step 1: Risk Stratification Using the Four-Group Approach

[0108] To further achieve risk stratification and validate the combined predictive value, all subjects were divided into four groups based on the median values ​​of serum uric acid and SIRI as pre-defined cutoff values:

[0109] Group 1: Low serum uric acid combined with low SIRI (UA < median and SIRI < median).

[0110] Group 2: Low serum uric acid combined with high SIRI (UA < median and SIRI ≥ median);

[0111] Group 3: High serum uric acid combined with low SIRI (UA ≥ median and SIRI < median);

[0112] Group 4: Hyperuricemia combined with high SIRI (UA ≥ median and SIRI ≥ median).

[0113] Step Two: Risk Assessment

[0114] Using Group 1 as the control group, weighted Cox regression analysis was used to calculate and compare the risk ratios of gout attacks in Groups 2 through 4. This analysis aimed to determine whether the coexistence of "high serum uric acid" and "high SIRI" would produce a synergistic amplification effect, thereby identifying the subject subgroup with the highest risk of acute and frequent gout attacks.

[0115] The analysis showed that the hazard ratio (HR) for acute gout attacks in the high UA combined with high SIRI group was significantly higher than that in the group with either single elevated indicator. The HR for frequent attacks also showed a similar trend, indicating a clear synergistic amplification effect between the two. This group was classified as the high gout attack risk group.

[0116] Step 3: Application of the Method

[0117] In actual clinical application, the risk assessment of gout attacks for any subject is carried out according to the following procedure:

[0118] (1) Obtain the baseline serum uric acid concentration data and blood routine test data of the subject, and extract neutrophil count, monocyte count and lymphocyte count from the blood routine data;

[0119] (2) Calculate the subject’s systemic immune inflammation index according to the formula SIRI = neutrophil count × monocyte count / lymphocyte count;

[0120] (3) Compare the subject's serum uric acid concentration with the preset median threshold for serum uric acid, and compare the subject's SIRI value with the preset median threshold for SIRI.

[0121] (4) Determine the risk group to which the subject belongs based on the comparison results. If the subject's serum uric acid concentration is higher than the preset threshold and the SIRI is also higher than the preset threshold, the subject is identified as a high-risk group for gout attacks. It is recommended that the clinical staff provide stricter uric acid-lowering treatment targets, closer anti-inflammatory interventions, and more frequent regular follow-up monitoring.

[0122] VII. Verification of the technical effectiveness of the method

[0123] Through the above research plan and data analysis, the method of the present invention has achieved the following key results:

[0124] (i) The synergistic effect of the two indicators has been confirmed.

[0125] The risk of acute gout attacks was significantly higher in the group with both high UA and high SIRI than in the group with only one elevated indicator, confirming a synergistic amplification effect between the two. This validates the scientific validity and necessity of a combined assessment of "metabolic burden + inflammatory status".

[0126] (ii) The independent predictive value has been confirmed

[0127] After adjusting for various confounding factors using a three-level multivariate Cox regression model, the independent association between SIRI and the risk of gout attacks remained significant, indicating that SIRI, as a systemic inflammatory marker, has predictive value for gout attacks independent of serum uric acid.

[0128] (iii) The linear dose-response relationship is clear.

[0129] Restricted cubic spline analysis showed that both serum uric acid and SIRI exhibited a linear dose-response relationship with the risk of gout attacks, with no significant nonlinear threshold effect observed. This implies that higher values ​​correlate with a greater risk of attacks, and clinicians can reassess the risk at any time based on dynamic changes in these indicators.

[0130] (iv) Easy to operate and easy to promote

[0131] Serum uric acid and routine blood tests are both routine clinical tests, requiring no additional complex testing equipment or costs. The method of this invention can be directly integrated into existing clinical diagnosis and treatment processes.

[0132] Embodiments of the device

[0133] The present invention also provides a device for predicting the risk of gout attacks based on joint prediction, comprising:

[0134] The data acquisition module is used to acquire biological sample test data of the subject, which includes at least serum uric acid concentration data and peripheral blood cell count data for calculating the systemic immune inflammation index.

[0135] The index calculation module is used to calculate the subject's systemic immune inflammation index based on the neutrophil count, monocyte count, and lymphocyte count in the peripheral blood cell count data, according to the formula SIRI = neutrophil count × monocyte count / lymphocyte count.

[0136] The comparison module is used to compare the subject's serum uric acid concentration with a preset serum uric acid threshold, and to compare the subject's SIRI value with a preset SIRI threshold. The preset threshold can be the median serum uric acid and SIRI values ​​of the population cohort to which the subject belongs.

[0137] The stratification module is used to divide subjects into different risk groups based on the comparison results. Subjects with serum uric acid concentrations and SIRIs above the preset thresholds are classified into the high-risk group for gout attacks. The remaining subjects are classified into low-risk, moderate-risk, or high-risk groups based on the combination of the two indicators relative to the preset thresholds.

[0138] Examples of computer-readable storage media

[0139] The present invention also provides a computer-readable storage medium having a computer program stored thereon. When executed by a processor, the program can implement all or part of the steps of the methods described in the above embodiments.

[0140] The computer-readable storage media include, but are not limited to, USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0141] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for predicting the risk of gout attacks based on joint prediction, characterized in that, Includes the following steps: Step 1: Obtain biological sample test data from the subject. The biological sample test data includes at least serum uric acid concentration data and peripheral blood cell count data used to calculate the systemic immune inflammation index (SIRI). Step 2: Based on the neutrophil count, monocyte count, and lymphocyte count in the peripheral blood cell count data, calculate the subject's systemic immune inflammation index (SIRI). The calculation formula is: SIRI = neutrophil count × monocyte count / lymphocyte count. Step 3: Compare the subject's serum uric acid concentration with a preset serum uric acid threshold, and compare the subject's SIRI value with a preset SIRI threshold. Step 4: Based on the comparison results, the subjects are divided into different risk groups. Subjects whose serum uric acid concentration is higher than the serum uric acid threshold and whose SIRI is higher than the SIRI threshold are divided into the high risk group for gout attacks.

2. The method for predicting gout attack risk based on joint prediction according to claim 1, characterized in that: The preset serum uric acid threshold value mentioned in step three is the median serum uric acid value of the population cohort to which the subject belongs; the preset SIRI threshold value is the median SIRI value of the population cohort to which the subject belongs.

3. The method for predicting gout attack risk based on joint prediction according to claim 1, characterized in that: The different risk groups mentioned in step four specifically include: Low serum uric acid combined with low SIRI group; Low serum uric acid combined with high SIRI group; High serum uric acid combined with low SIRI group; and The group with high serum uric acid and high SIRI was classified as the high risk group for gout attacks.

4. The method for predicting gout attack risk based on joint prediction according to claim 3, characterized in that: The method further includes: using the low serum uric acid combined with low SIRI group as the reference group, calculating the risk ratio (HR) of gout attacks for the remaining groups using a multivariate Cox proportional hazards regression model, in order to quantitatively assess the relative risk of gout attacks for each group of subjects.

5. The method for predicting gout attack risk based on joint prediction according to claim 4, characterized in that: The multivariate Cox proportional hazards regression model is a model that is stepwise adjusted for confounding factors, which include one or more of the following: age, family history of gout, disease duration, tophi, systolic blood pressure, diastolic blood pressure, body mass index, triglycerides, total cholesterol, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, fasting blood glucose, estimated glomerular filtration rate, and C-reactive protein.

6. The method for predicting gout attack risk based on joint prediction according to claim 1, characterized in that: The subjects were male patients with gout; the risk of gout attacks included the risk of acute gout attacks and / or the risk of frequent gout attacks.

7. The method for predicting gout attack risk based on joint prediction according to claim 1, characterized in that: The biological sample test data of the subject in step one refers to the baseline test data of the subject before receiving uric acid-lowering treatment.

8. The method for predicting gout attack risk based on joint prediction according to claim 1, characterized in that: The method further includes: using a restricted cubic spline model to assess the dose-response relationship between serum uric acid concentration and / or SIRI and the risk of gout attacks.

9. A device for predicting the risk of gout attacks based on joint prediction, characterized in that, include: The data acquisition module is used to acquire biological sample test data of the subject, which includes at least serum uric acid concentration data and peripheral blood cell count data for calculating the systemic immune inflammation index (SIRI). The index calculation module is used to calculate the subject's systemic immune inflammation index (SIRI) based on the neutrophil count, monocyte count and lymphocyte count in the peripheral blood cell count data. The calculation formula is: SIRI = neutrophil count × monocyte count / lymphocyte count. The comparison module is used to compare the subject's serum uric acid concentration value with a preset serum uric acid threshold value, and to compare the subject's SIRI value with the preset SIRI threshold value. The stratification module is used to divide the subjects into different risk groups based on the comparison results. Subjects whose serum uric acid concentration is higher than the serum uric acid threshold and whose SIRI is higher than the SIRI threshold are classified as the high risk group for gout attacks.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the steps of the method according to any one of claims 1 to 8.

Images