A method and system for assessing the risk of gout flare based on neutrophil to lymphocyte ratio

Abstract

The application provides a gout recurrence risk assessment method and system based on a neutrophil-to-lymphocyte ratio, comprising: data acquisition, data preprocessing, and generating gout recurrence risk assessment sample data through data standardization processing; establishing a joint model of a Cox proportional hazards regression model and a competing risk model to evaluate the correlation between the neutrophil-to-lymphocyte ratio (NLR) and gout recurrence; adding NLR as a characteristic variable of a prognosis factor of gout recurrence risk to a baseline model to construct multiple gout recurrence risk candidate prediction models; screening to obtain a target gout recurrence risk assessment model; generating an evaluation result; and visual display. The method can effectively handle the problems of incomplete and skewed distribution of clinical data, improve the quality and stability of the data, improve the accuracy of evaluation and prediction by screening out an effective target gout recurrence risk assessment model, and provide reliable auxiliary decision support for clinicians.

Description

A method and system for assessing the risk of gout recurrence based on the neutrophil-to-lymphocyte ratio. Technical Field

[0001] This application relates to the field of model prediction technology, and in particular to a method and system for assessing the risk of gout recurrence based on the ratio of neutrophils to lymphocytes. Background Technology

[0002] Gout is a chronic inflammatory disease affecting approximately 55.8 million people worldwide, with about 70% of gout patients experiencing uncontrolled symptoms. Its recurrent nature and associated complications, such as cardiovascular disease and kidney damage, pose significant challenges to clinical management. Traditional biomarkers such as serum uric acid (UA) levels and tophi are commonly used to monitor gout. However, these indicators have limitations in predicting gout recurrence, particularly in patients with normal serum uric acid levels or those receiving uric acid-lowering therapy, thus providing insufficient guidance for the use of anti-inflammatory drugs. This highlights the need for more reliable, sensitive biomarkers with higher predictive accuracy to better guide treatment strategies for preventing gout recurrence.

[0003] Recent studies on the pathophysiology of gout have shown that inflammation and immune dysregulation are key drivers of disease recurrence. The neutrophil-to-lymphocyte ratio (NLR), as an readily available biomarker, has demonstrated prognostic value in various inflammatory diseases due to its ability to reflect the balance between inflammatory responses and immune regulation in the body. However, to date, no studies have definitively demonstrated the superiority of NLR in predicting gout recurrence, highlighting the need for further research to clarify its potential role in gout management. This is particularly important given that traditional biomarkers (such as UA and tophi) and common inflammatory markers (such as C-reactive protein [CRP]) have proven insufficient to reliably predict gout recurrence.

[0004] Therefore, rigorously evaluating the predictive value of NLR for gout recurrence, comparing its effectiveness with that of traditional biomarkers (including UA, CRP, and tophi), and developing predictive models to assess whether the predictive utility of NLR remains effective in specific clinical contexts, such as in patients with normal UA levels, no tophi, and receiving uric acid-lowering therapy, is an important area of ​​research for professionals in this field. Summary of the Invention

[0005] In view of this, it is necessary to provide a method and system for assessing the risk of gout recurrence based on the neutrophil-to-lymphocyte ratio, including: data acquisition, data preprocessing, and generating sample data for gout recurrence risk assessment through data standardization; establishing a joint model of Cox proportional hazards regression and competing hazard models to assess the association between the neutrophil-to-lymphocyte ratio (NLR) and gout recurrence; incorporating NLR as a characteristic variable of the prognostic factor for gout recurrence risk into the baseline model to construct multiple candidate predictive models for gout recurrence risk; screening to obtain a target gout recurrence risk assessment model; generating assessment results; and visualization. This method can effectively address the incompleteness and skewed distribution of clinical data, improve data quality and stability, and improve the accuracy of assessment and prediction by selecting an effective target gout recurrence risk assessment model, thus providing reliable auxiliary decision support for clinicians.

[0006] This study aims to rigorously evaluate the predictive value of NLR for gout recurrence and compare its effectiveness with that of traditional biomarkers, including UA, CRP, and tophi. Furthermore, subgroup analyses will be conducted and predictive models will be developed to assess whether the predictive utility of NLR remains effective in specific clinical contexts, such as in patients with normal UA levels, no tophi, and receiving uric acid-lowering therapy.

[0007] In a first aspect, embodiments of this application provide a method for assessing the risk of gout recurrence based on the neutrophil-to-lymphocyte ratio, the method comprising:

[0008] S1, collect electronic medical record data, clinical pathology data, hospitalization and clinical follow-up data of the same target population within a preset time period from the data center system;

[0009] S2, preprocess the electronic medical record data, clinical pathology data, hospitalization and clinical follow-up data, and generate gout recurrence risk assessment sample data through data standardization processing;

[0010] S3. A combined model of Cox proportional hazards regression and competing hazard model was established to assess the association between the neutrophil-to-lymphocyte ratio (NLR) and gout recurrence.

[0011] S4. When the assessment of the association judgment condition is passed, NLR is added as a characteristic variable of the prognostic factor of gout recurrence risk to the baseline model to construct multiple candidate prediction models for gout recurrence risk.

[0012] S5. The C-statistic, Net Reclassification Index (NRI), and Integrated Discriminant Improvement Index (IDI) are used to evaluate the predictive effect of the various candidate models for gout recurrence risk to obtain the target gout recurrence risk assessment model.

[0013] S6. Based on the patient's clinical data and the target gout recurrence risk assessment model, predict the patient's risk of gout recurrence and generate the corresponding risk assessment results.

[0014] S7. Construct a visualization interface to display and evaluate the optimal threshold and predictive value of the neutrophil-to-lymphocyte ratio (NLR) for gout recurrence, and compare its efficacy with traditional biomarkers.

[0015] Optionally, in another implementation of the first aspect of the present invention, in step S1, the same target population is a set of hospitalized patients with gout symptoms, ranging from those without gout symptoms to those with gout symptoms. The electronic medical record data includes: neutrophil-to-lymphocyte ratio (NLR), gout recurrence time, recurrence status, and covariates, including: demographic characteristics, lifestyle factors, laboratory tests, physical examinations, comorbidities, and medication use.

[0016] Optionally, in another implementation of the first aspect of the present invention, step S2 involves preprocessing the electronic medical record data, clinical pathology data, hospitalization and clinical follow-up data, and generating gout recurrence risk assessment sample data through data standardization processing, including:

[0017] Use box plots to identify outliers and remove them using IQR rules.

[0018] Visualize the distribution of missing values ​​in the data and perform imputation.

[0019] The imputed data is then standardized using the following formula:

[0020] ,

[0021] in This is the original data. The average of the raw data, The standard deviation of the original data;

[0022] The standardized data were subjected to statistical analysis. The normality of continuous variables was assessed using the Shapiro-Wilk test. The independent t-test or non-parametric test was used to compare continuous variables among different NLR groups. Categorical variables were analyzed using the chi-square test or Fisher's exact test. Missing data were processed using the chain equation multiple imputation method (MICE) combined with the classification and regression tree (CART) method. The results of each imputation dataset were then combined to obtain the final estimate.

[0023] Optionally, in another implementation of the first aspect of the present invention, step S3, establishing a Cox proportional hazards regression model and a competing hazard model to assess the association between the neutrophil-to-lymphocyte ratio (NLR) and gout recurrence, includes:

[0024] S3.1, The Lasso method is used to select the variables that have the greatest influence on the model, including: The goal of the Lasso method is to minimize the following loss function:

[0025] ,

[0026] in, It is the first The target value of each observation. It is the first The first observation One characteristic, It is the intercept term. It is the first The regression characteristic coefficients of each feature, These are regularization parameters that control the strength of regularization. It is the sample size. It is the number of features, and the L1 regularization term. This allows some coefficients to be compressed to zero, thereby achieving feature selection and obtaining the dataset. ;

[0027] S3.2, Substitute the filtered data into the Cox proportional hazards regression model to obtain the regression characteristic coefficients. Among them, the estimator satisfy:

[0028] ,

[0029] in, This represents the sample composition of the Cox model. , Indicates the first A period of survival, Indicates the time of deletion. Represents an event identifier vector;

[0030] S3.3, using regression characteristic coefficients For dataset Through formula Transformation to obtain a new dataset ;

[0031] S3.4, Divide the new dataset into a training set and a validation set according to a preset ratio;

[0032] S3.5, The competitive risk model is trained using the training set and tested and evaluated using the validation set to obtain the competitive risk model;

[0033] S3.6, the optimal cutoff value for NLR was determined using the Grey test statistic maximization method in the competing risk model and the log-rank test statistic maximization method in the Cox proportional hazards survival model. Sensitivity analysis was performed using the competing risk model and Kaplan-Meier survival analysis to confirm the robustness of the research results under different model settings.

[0034] Optionally, in another implementation of the first aspect of the present invention, in step S4, when the evaluation association judgment condition is passed, NLR is added as a characteristic variable of the prognostic factor for gout recurrence risk to the baseline model to construct multiple candidate prediction models for gout recurrence risk, including:

[0035] The assessment correlation judgment conditions are as follows:

[0036] To determine whether the neutrophil-to-lymphocyte ratio (NLR) is associated with an increased risk of gout recurrence during hospitalization, and whether it improves predictive accuracy compared to traditional markers such as serum uric acid (UA) levels, tophi, and C-reactive protein (CRP).

[0037] Optionally, in another implementation of the first aspect of the present invention, step S5 uses the C-statistic, the Net Reclassification Index (NRI), and the Integrated Discriminant Improvement Index (IDI) to evaluate the predictive effectiveness of the various candidate gout recurrence risk prediction models for assessing gout recurrence, in order to obtain a target gout recurrence risk assessment model, including:

[0038] Construct multiple candidate prediction models for the risk of gout recurrence, including at least: Cox regression model, support vector machine (SVM) model, k-nearest neighbor (KNN) model, random survival forest model, and XGBoost model;

[0039] The incremental predictive performance of NLR was evaluated and compared using the C-statistic, the net heavy classification index (NRI), and the comprehensive discriminant improvement index (IDI), and a coarse screening of various candidate predictive models for gout recurrence risk was conducted.

[0040] The prediction accuracy was evaluated by generating ROC curves for each candidate prediction model for gout recurrence risk and calculating the area under the curve (AUC) for each model.

[0041] The differences in AUCs were compared using the DeLong test.

[0042] The candidate prediction model with the best performance was selected as the target model for assessing the risk of gout recurrence.

[0043] The net reclassification improved NRI and comprehensive identification improved IDI indices were calculated to assess the incremental predictive value of incorporating NLR into the baseline model, and confidence intervals were obtained through guided resampling to optimize the target gout recurrence risk assessment model.

[0044] Optionally, in another implementation of the first aspect of the present invention, step S6, predicting the patient's risk of gout recurrence based on the patient's clinical data and the target gout recurrence risk assessment model, and generating a corresponding risk assessment result, includes:

[0045] Input the patient's clinical data into the target gout recurrence risk assessment model;

[0046] Output the potential risk assessment results.

[0047] Secondly, embodiments of this application provide a gout recurrence risk assessment system based on the neutrophil-to-lymphocyte ratio, applied to a gout recurrence risk assessment method based on the neutrophil-to-lymphocyte ratio as described in the first aspect, characterized in that the system comprises:

[0048] The data acquisition module is used to collect electronic medical record data, clinical pathology data, hospitalization and clinical follow-up data of the same target population within a preset time period from the data center system.

[0049] The data processing module is used to preprocess the electronic medical record data, clinical pathology data, hospitalization and clinical follow-up data, and generate gout recurrence risk assessment sample data through data standardization processing;

[0050] The NLR assessment module is used to build a joint model of Cox proportional hazards regression model and competing hazard model to assess the association between the neutrophil to lymphocyte ratio (NLR) and gout recurrence.

[0051] The model building module is used to add NLR as a prognostic factor for gout recurrence risk to the baseline model when the assessment criteria are met, in order to build multiple candidate predictive models for gout recurrence risk.

[0052] The model selection module is used to evaluate the predictive effect of the various candidate models for gout recurrence risk using the C-statistic, the net reclassification index (NRI), and the comprehensive discriminant improvement index (IDI) to obtain the target gout recurrence risk assessment model.

[0053] The risk assessment module is used to predict the risk of gout recurrence in patients based on their clinical data and the target gout recurrence risk assessment model, and to generate corresponding risk assessment results.

[0054] The comparison display module is used to construct and display a visualization interface to evaluate the optimal threshold and predictive value of the neutrophil-to-lymphocyte ratio (NLR) for gout recurrence and compare its efficacy with traditional biomarkers.

[0055] Thirdly, embodiments of this application provide an electronic device, including:

[0056] processor;

[0057] Memory used to store processor-executable instructions;

[0058] The processor is configured to implement, when executing the instructions, a method for assessing the risk of gout recurrence based on the ratio of neutrophils to lymphocytes as described in the first aspect.

[0059] Fourthly, embodiments of this application provide a computer-readable storage medium storing a program that instructs a device to perform a gout recurrence risk assessment method based on the neutrophil-to-lymphocyte ratio as described in any one of claims 1 to 7.

[0060] The method and system for assessing the risk of gout recurrence based on the neutrophil-to-lymphocyte ratio provided in this application collect electronic medical record data, clinical pathology data, and hospitalization and clinical follow-up data of the same target population within a preset time period from a data center system; preprocess the electronic medical record data, clinical pathology data, and hospitalization and clinical follow-up data, and generate gout recurrence risk assessment sample data through data standardization; establish a joint model of Cox proportional hazards regression model and competing hazard model to assess the association between the neutrophil-to-lymphocyte ratio (NLR) and gout recurrence; when the association assessment criteria are met, NLR is used as a measure of gout recurrence. Characteristic variables of prognostic factors were incorporated into a baseline model to construct multiple candidate predictive models for gout recurrence risk. The C-statistic, Net Reclassification Index (NRI), and Integrated Discriminant Improvement Index (IDI) were used to evaluate the predictive efficacy of these models, resulting in a target gout recurrence risk assessment model. Based on patient clinical data and the target model, the risk of gout recurrence was predicted, generating corresponding risk assessment results. A visualization interface was constructed and displayed to evaluate the optimal threshold and predictive value of the neutrophil-to-lymphocyte ratio (NLR) for gout recurrence, comparing its efficacy with traditional biomarkers. This method effectively addresses the incompleteness and skewed distribution of clinical data, improving data quality and stability. By selecting an effective target gout recurrence risk assessment model, it enhances the accuracy of prediction and provides reliable decision support for clinicians. Attached Figure Description

[0061] Figure 1 is a flowchart of a gout recurrence risk assessment method based on the ratio of neutrophils to lymphocytes provided in another embodiment of this application.

[0062] Figure 2 shows the distribution and predictive value of the neutrophil-to-lymphocyte ratio (NLR) provided in an embodiment of this application in determining the optimal cutoff time and the risk of gout recurrence during hospitalization.

[0063] Figure 3 shows the cumulative incidence and Kaplan-Meier survival curves of gout recurrence during hospitalization in the GoutRe cohort and MIMIC-Ⅳ cohort, provided in another embodiment of this application.

[0064] Figure 4 is a stratified analysis diagram of the GoutRe and MIMIC-IV cohorts by age, sex, eGFR, UA level, and comorbidities provided in an embodiment of this application.

[0065] Figure 5 shows the NLR ROC curves for predicting gout recurrence during hospitalization in the GoutRe and MIMIC-IV cohorts, provided by an embodiment of this application.

[0066] Figure 6 is a schematic diagram of a gout recurrence risk assessment system module based on the ratio of neutrophils to lymphocytes provided in an embodiment of this application.

[0067] Figure 7 is a schematic diagram of an electronic terminal device provided in an embodiment of this application. Detailed Implementation

[0068] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them.

[0069] It should be noted that, in the embodiments of this application, "at least one" refers to one or more, and "more than one" refers to two or more. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the specification of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application.

[0070] It should be noted that in the embodiments of this application, the terms "first," "second," etc., are used only for descriptive purposes and should not be construed as indicating or implying relative importance, nor as indicating or implying order. Features specified as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0071] Based on the embodiments described in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0072] This application provides a method and system for assessing the risk of gout recurrence based on the ratio of neutrophils to lymphocytes. It can effectively address the problems of incomplete and skewed distribution of clinical data, improve the quality and stability of data, and improve the accuracy of assessment and prediction by screening out effective target gout recurrence risk assessment models, thus providing reliable auxiliary decision support for clinicians.

[0073] Figure 1 is a flowchart of a gout recurrence risk assessment method based on the neutrophil-to-lymphocyte ratio according to an embodiment of this application. As shown in Figure 1, a gout recurrence risk assessment method based on the neutrophil-to-lymphocyte ratio includes:

[0074] S1 collects electronic medical record data, clinical pathology data, hospitalization and clinical follow-up data of the same target population within a preset time period from the data center system.

[0075] Specifically, in this embodiment of the application, in step S1, the same target population is a set of hospitalized patients with gout symptoms, ranging from those without gout symptoms to those with gout symptoms. The electronic medical record data includes: neutrophil-to-lymphocyte ratio (NLR), gout recurrence time, recurrence status, and covariates. The covariates include: demographic characteristics, lifestyle factors, laboratory tests, physical examinations, comorbidities, and medication use.

[0076] S2, preprocess the electronic medical record data, clinical pathology data, hospitalization and clinical follow-up data, and generate gout recurrence risk assessment sample data through data standardization processing.

[0077] Specifically, in this embodiment, step S2 preprocesses the electronic medical record data, clinical pathology data, hospitalization and clinical follow-up data, and generates gout recurrence risk assessment sample data through data standardization processing, including:

[0078] Use box plots to identify outliers and remove them using IQR rules.

[0079] Visualize the distribution of missing values ​​in the data and perform imputation.

[0080] The imputed data is then standardized using the following formula:

[0081] ,

[0082] in This is the original data. The average of the raw data, The standard deviation of the original data;

[0083] The standardized data were subjected to statistical analysis. The normality of continuous variables was assessed using the Shapiro-Wilk test. The independent t-test or non-parametric test was used to compare continuous variables among different NLR groups. Categorical variables were analyzed using the chi-square test or Fisher's exact test. Missing data were processed using the chain equation multiple imputation method (MICE) combined with the classification and regression tree (CART) method. The results of each imputation dataset were then combined to obtain the final estimate.

[0084] S3. A combined model of Cox proportional hazards regression and competing hazard model was established to assess the association between the neutrophil-to-lymphocyte ratio (NLR) and gout recurrence.

[0085] Specifically, in the embodiments of this application, step S3, establishing a Cox proportional hazards regression model and a competing hazard model to assess the association between the neutrophil-to-lymphocyte ratio (NLR) and gout recurrence, includes:

[0086] S3.1, The Lasso method is used to select the variables that have the greatest influence on the model, including: The goal of the Lasso method is to minimize the following loss function:

[0087] ,

[0088] in, It is the first The target value of each observation. It is the first The first observation One characteristic, It is the intercept term. It is the first The regression characteristic coefficients of each feature, These are regularization parameters that control the strength of regularization. It is the sample size. It is the number of features, and the L1 regularization term. This allows some coefficients to be compressed to zero, thereby achieving feature selection and obtaining the dataset. ;

[0089] S3.2, Substitute the filtered data into the Cox proportional hazards regression model to obtain the regression characteristic coefficients. Among them, the estimator satisfy:

[0090] ,

[0091] in, This represents the sample composition of the Cox model. , Indicates the first A period of survival, Indicates the time of deletion. Represents an event identifier vector;

[0092] S3.3, using regression characteristic coefficients For dataset Through formula Transformation to obtain a new dataset ;

[0093] S3.4, Divide the new dataset into a training set and a validation set according to a preset ratio;

[0094] S3.5, The competitive risk model is trained using the training set and tested and evaluated using the validation set to obtain the competitive risk model;

[0095] S3.6, the optimal cutoff value for NLR was determined using the Grey test statistic maximization method in the competing risk model and the log-rank test statistic maximization method in the Cox proportional hazards survival model. Sensitivity analysis was performed using the competing risk model and Kaplan-Meier survival analysis to confirm the robustness of the research results under different model settings.

[0096] Specifically, the model training process mainly consists of four steps: 1. Pre-training phase; 2. Supervised fine-tuning, also known as instruction fine-tuning phase; 3. Reward model training phase; 4. Reinforcement learning fine-tuning phase. The specific training steps include: 1) Data acquisition and preprocessing: collecting and organizing the dataset needed for training; 2) Model design and construction: designing and building a suitable model according to task requirements; 3) Model training: training the model using the training dataset, continuously adjusting the model parameters to enable the model to better fit the data; 4) Model evaluation and optimization: evaluating the trained model using the test dataset and optimizing the model based on the evaluation results; 5) Model deployment and use: deploying the trained model to real-world application scenarios and applying it.

[0097] S4. When the assessment of the association judgment condition is passed, NLR is added to the baseline model as a characteristic variable of the prognostic factor of gout recurrence risk to construct multiple candidate prediction models for gout recurrence risk.

[0098] Specifically, in the embodiments of this application, in step S4, when the assessment correlation judgment condition is passed, NLR is added as a characteristic variable of the prognostic factor for gout recurrence risk to the baseline model to construct multiple candidate prediction models for gout recurrence risk, including:

[0099] The assessment correlation judgment conditions are as follows:

[0100] To determine whether the neutrophil-to-lymphocyte ratio (NLR) is associated with an increased risk of gout recurrence during hospitalization, and whether it improves predictive accuracy compared to traditional markers such as serum uric acid (UA) levels, tophi, and C-reactive protein (CRP).

[0101] S5. The C-statistic, Net Reclassification Index (NRI), and Integrated Discriminant Improvement Index (IDI) are used to evaluate the predictive effect of the various candidate models for gout recurrence risk to obtain the target gout recurrence risk assessment model.

[0102] Specifically, in this embodiment, step S5 uses the C-statistic, Net Reclassification Index (NRI), and Integrated Discriminant Improvement Index (IDI) to evaluate the predictive effectiveness of the various candidate gout recurrence risk prediction models, thereby obtaining a target gout recurrence risk assessment model, including:

[0103] Construct multiple candidate prediction models for the risk of gout recurrence, including at least: Cox regression model, support vector machine (SVM) model, k-nearest neighbor (KNN) model, random survival forest model, and XGBoost model;

[0104] The incremental predictive performance of NLR was evaluated and compared using the C-statistic, the net heavy classification index (NRI), and the comprehensive discriminant improvement index (IDI), and a coarse screening of various candidate predictive models for gout recurrence risk was conducted.

[0105] The prediction accuracy was evaluated by generating ROC curves for each candidate prediction model for gout recurrence risk and calculating the area under the curve (AUC) for each model.

[0106] The differences in AUCs were compared using the DeLong test.

[0107] The candidate prediction model with the best performance was selected as the target model for assessing the risk of gout recurrence.

[0108] The net reclassification improved NRI and comprehensive identification improved IDI indices were calculated to assess the incremental predictive value of incorporating NLR into the baseline model, and confidence intervals were obtained through guided resampling to optimize the target gout recurrence risk assessment model.

[0109] S6. Based on the patient's clinical data and the target gout recurrence risk assessment model, predict the patient's risk of gout recurrence and generate the corresponding risk assessment results.

[0110] Specifically, in this embodiment, step S6 involves predicting the patient's risk of gout recurrence based on the patient's clinical data and the target gout recurrence risk assessment model, and generating corresponding risk assessment results, including:

[0111] Input the patient's clinical data into the target gout recurrence risk assessment model;

[0112] Output the potential risk assessment results.

[0113] S7. Construct a visualization interface to display and evaluate the optimal threshold and predictive value of the neutrophil-to-lymphocyte ratio (NLR) for gout recurrence, and compare its efficacy with traditional biomarkers.

[0114] Experiment 1

[0115] This study aims to rigorously evaluate the predictive value of NLR for gout recurrence and compare its effectiveness with that of traditional biomarkers, including UA, CRP, and tophi. Furthermore, subgroup analyses will be conducted and predictive models will be developed to assess whether the predictive utility of NLR remains effective in specific clinical contexts, such as in patients with normal UA levels, no tophi, and receiving uric acid-lowering therapy.

[0116] This retrospective study was based on two cohorts: the GoutRe cohort, which included patients from five hospitals; and the MIMIC-IV cohort, which contained deidentified health-related data from a range of hospitalized patients. The GoutRe cohort included patients hospitalized between January 1, 2010, and July 30, 2024, while the MIMIC-IV cohort used data from 2008 to 2019. Including a diverse population enhanced the generalizability and robustness of the findings.

[0117] This international, multicenter, retrospective cohort study included gout patients from five hospitals in China (GoutRe cohort) and the MIMIC-IV database (MIMIC-IV cohort) for external validation. Participants in both cohorts were diagnosed with gout according to the 1977 ACR and / or 2015 ACR / EULAR classification criteria for gout. The GoutRe cohort included patients hospitalized between January 1, 2010, and July 30, 2024, while the MIMIC-IV cohort used data collected between 2008 and 2019.

[0118] A total of 97,086 patients across the two cohorts (GoutRe cohort = 78,140; MIMIC-IV cohort = 18,946) met the 1977 ACR and / or 2015 ACR / EULAR gout classification criteria and had a gout-related ICD-10 code on their discharge diagnosis. Exclusion criteria included acute gout attacks, chronic gouty arthritis, other autoimmune diseases, other musculoskeletal diseases requiring nonsteroidal anti-inflammatory drugs or glucocorticoids, reported joint pain without a clear diagnosis, difficulty in identifying a gout attack, and length of hospital stay (LOS) of less than 3 days (eFigure 1 in Supplementary Materials). After applying the exclusion criteria, the GoutRe cohort initially included 6,526 patients, and the MIMIC-IV cohort initially included 6,475 patients.

[0119] Patients with missing NLR values ​​(301 in the GoutRe cohort and 3,286 in the MIMIC-IV cohort) or missing data exceeding 30% (641 in the GoutRe cohort) were further excluded. Additionally, patients who died during hospitalization (597 in the MIMIC-IV cohort) or were transferred to the ICU (583 in the MIMIC-IV cohort) were excluded, resulting in a final study population of 5,584 patients in the GoutRe cohort and 2,019 patients in the MIMIC-IV cohort (eFigure 1 in the supplementary materials).

[0120] Covariates included demographic characteristics, lifestyle factors, laboratory tests, physical examination, comorbidities, and medication use. Demographic characteristics included age, sex, race, and weight changes. Lifestyle factors included smoking and alcohol consumption history. Laboratory tests included complete blood count parameters and renal function tests. Physical examination findings included the presence of tophi. Comorbidities assessed included hypertension, diabetes, cardiovascular disease, heart failure, stroke, dyslipidemia, fatty liver, kidney disease, thyroid disease, cancer, history of kidney stones, and metabolic syndrome. Medication use included antigout medications, hypoglycemic agents, cardiovascular medications, anticoagulants, lipid-lowering agents, and mannitol.

[0121] Measurement of NLR: In the GoutRe cohort, baseline NLR values ​​were determined on the first day of admission, before the initiation of any treatment. Neutrophil and lymphocyte counts were obtained from blood samples by complete blood count analysis and reported in ×10³ cells / µL. NLR was calculated by dividing the absolute neutrophil count by the absolute lymphocyte count. In the MIMIC-IV database, experimental data from patients with recurrent gout were selected and analyzed from the earliest available records after admission, confirming that the data were collected prior to a gout attack. The calculation method was the same as described above.

[0122] Statistical Analysis: First, the normality of continuous variables was assessed using the Shapiro-Wilk test. Where necessary, independent t-tests or nonparametric tests were used to compare continuous variables among different NLR groups. Categorical variables were analyzed using the chi-square test or Fisher's exact test. Missing data were processed using the chain equation multiple imputation method (MICE) combined with the classification and regression tree (CART) method, and the results of each imputed dataset were combined to obtain the final estimate. The optimal cutoff value for NLR was determined using the Grey test statistic maximization method in the competing hazard model and the log-rank test statistic maximization method in the Cox proportional hazard survival model. Sensitivity analyses were performed using the competing hazard model and Kaplan-Meier survival analysis to confirm the robustness of the results under different model settings.

[0123] To assess the association between NLR and gout recurrence, Cox proportional hazards regression models were used to calculate hazard ratios (HRs), 95% confidence intervals (CIs), and p-values. Model 1 was unadjusted; Model 2 adjusted for NLR, serum uric acid (UA), estimated glomerular filtration rate (eGFR), and tophi; Model 3 further adjusted for age, sex, smoking history, alcohol consumption history, and comorbidities (such as hypertension, diabetes, and cardiovascular disease). Subgroup analyses explored the consistency of the NLR effect across age, sex, and comorbidities. Interaction p-values ​​were calculated using likelihood ratio tests, comparing models with and without interaction terms for each stratified factor.

[0124] To further evaluate predictive performance, machine learning models were employed in addition to the traditional Cox regression model. These included Random Survival Forest, Support Vector Machine (SVM), k-Nearest Neighbors (KNN), and XGBoost models. Predictive accuracy was assessed by generating ROC curves and calculating the area under the curve (AUC) for each model. The DeLong test was used to compare the statistical significance of differences in AUC.

[0125] In addition, the Net Reclassification Improvement (NRI) and Integrated Identification Improvement (IDI) indices were calculated to assess the incremental predictive value of incorporating NLR into the baseline model, and confidence intervals were obtained through guided resampling. Decision curve analysis (DCA) was performed to evaluate the clinical utility of NLR-based models across a range of threshold probabilities, assessing the net benefit of various predictive models in a clinical context. All statistical tests were two-tailed, and a p-value less than 0.05 was considered statistically significant. All analyses were performed using R version 4.3.2 (R Statistical Items).

[0126] Primary Outcomes and Measured Measure: The primary outcome was the gout recurrence rate, assessed using inpatient and clinical follow-up data. Cox proportional hazards regression and competing hazard models were used to assess the association between NLR and gout recurrence. The incremental predictive performance of NLR was evaluated using the C-statistic, net reclassification index (NRI), and integrated discriminant improvement index (IDI), with additional comparisons made against various modeling methods, including XGBoost and Cox regression.

[0127] Results: A total of 7,603 participants were included (GoutRe cohort: 5,584; MIMIC-IV cohort: 2,019). In the GoutRe cohort, the relapse rate was higher in the high NLR group than in the low NLR group (39.7% vs. 20.1%; P < .001), and a similar result was observed in the MIMIC-IV cohort (18.2% vs. 10.1%; P < .001). Patients in the high NLR group were older (mean age 65.0 years vs. 60.5 years; P < .01) and had more comorbidities, such as tophi (7.97% vs. 3.83%; P < .01), kidney stones (44.0% vs. 40.5%; P < .01), and heart failure (8.52% vs. 3.65%; P < .01). The use of diuretics (24.49% vs. 9.13%; P < .01) and beta-blockers (27.96% vs. 18.57%; P < .01) was also more common.

[0128] In both the GoutRe cohort (HR, 2.05; 95% CI, 1.83–2.30; P < .001) and the MIMIC-IV cohort (HR, 2.84; 95% CI, 2.08–3.87; P < .001), elevated NLR was associated with an increased risk of gout recurrence. NLR was weakly positively correlated with CRP (R² = 0.091; P < .001), but not significantly correlated with UA (R² = 8.9e-05; P = .61). The AUC of NLR (0.629) was higher than that of UA (0.591) or CRP (0.613).

[0129] Subgroup analysis confirmed that elevated NLR was associated with a higher risk of gout recurrence in patients with normal UA levels (HR, 1.87; 95% CI, 1.45–2.41; P < .001) and those receiving urate-lowering therapy (HR, 2.15; 95% CI, 1.68–2.76; P < .001). Including NLR in the baseline model improved predictive accuracy (increased C-statistic: GoutRe from 0.65 to 0.68, P < .001; MIMIC-IV from 0.80 to 0.81, P = .003). NRI (0.12; P < .01) and IDI (0.05; P < .01) further supported the added value of NLR.

[0130] Conclusions and Significance: High NLR was significantly associated with an increased risk of gout recurrence during hospitalization. These findings suggest that NLR may serve as a simple, reliable, and readily available biomarker for identifying individuals at high risk of recurrence, supporting its potential application in guiding clinical management and customized treatment interventions.

[0131] This study included a total of 7,603 participants, comprising 5,584 patients from the GoutRe cohort (100% Asian; mean [SD] age, 62.7 [14.7] years; 86.3% male) and 2,019 patients from the MIMIC-IV cohort (predominantly white [72.9%]; mean [ST] age, 68.0 [12.9] years; 75.1% male). The GoutRe cohort consisted of 1,659 patients with recurrent gout and 3,925 with non-recurrent gout, while the MIMIC-IV cohort included 320 patients in the recurrent group and 1,699 patients in the non-recurrent group.

[0132] As shown in Figure 2, participants were divided into two groups (part C in Figure 2) based on the optimal NLR cutoff value of 2.69 determined by maximizing the log-rank test in the Cox proportional hazards model. In the GoutRe cohort, compared with the low NLR group (n=2848), patients in the high NLR group (n=2736) were older (mean [SD] age, 65.0[14.4] years vs 60.5[14.6] years, P<0.01), and had a higher incidence of gout recurrence (39.69% vs 20.12%, P<0.01), tophi (7.97% vs 3.83%, P<0.01), stones (44.0% vs 40.5%, P<0.01), and heart failure (8.52% vs 3.65%, P<0.01). They also showed higher serum uric acid levels (e.g., >10 mg / dL: 19.70% vs 16.22%, P<0.01), lower eGFR levels (e.g., ≥90 mL / min / 1.73 m²: 13.01% vs 26.54%, P<0.01), and more use of diuretics (24.49% vs 9.13%, P<0.01), beta-blockers (27.96% vs 18.57%, P<0.01), and NaHCO3 (30.30% vs 20.01%, P<0.01).

[0133] Similarly, in the MIMIC-IV cohort, compared with the low NLR group (n=582), the high NLR group had a higher rate of gout recurrence (18.16% vs. 10.14%, P<0.01), a higher prevalence of heart failure (41.61% vs. 29.73%, P<0.01), and more frequent use of diuretics (34.59% vs. 15.29%, P<0.01) and beta-blockers (10.58% vs. 5.84%, P<0.01). Baseline characteristics, including race, laboratory values ​​(e.g., UA, eGFR), and comorbidities, highlighted statistically significant differences between the high and low NLR groups (P<0.05).

[0134] The distribution of NLR in the GoutRe cohort is shown in Part B of Figure 2, with most values ​​concentrated between 2 and 3. A non-linear relationship exists between NLR and gout recurrence (Parts D and E of Figure 2), and the non-linearity is highly significant (P < 0.001). The optimal NLR cutoff value of 2.69 was determined by combining log-rank test maximization within the survival analysis framework and Gray's test within the competing risk model framework (Part C of Figure 2). The predictive importance of NLR is comparable to known predictors, including UA and tophi (Part A of Figure 2), a finding validated in the MIMIC-IV cohort, further supporting the robustness of NLR as an important predictor of gout recurrence (Part E of Figure 2).

[0135] The cumulative incidence of gout recurrence during hospitalization is shown in Figure 3. In both the GoutRe and MIMIC-IV cohorts, patients with elevated NLR showed a significantly higher risk of recurrence (log-rank P < 0.001). This association was consistent across all subgroups, including those with normal serum uric acid levels, those without tophi, those with normal serum UA levels but without tophi, and those receiving uric acid-lowering and anti-inflammatory treatments (Figures 4-5). Kaplan-Meier survival curves (Figures 3 and 4) further support these observations, demonstrating a strong association between elevated NLR and increased recurrence rates across various clinical settings. In the multivariate Cox model, elevated NLR was independently associated with an increased risk of recurrence (GoutRe: HR, 2.05; 95% CI, 1.83–2.30; P < 0.01; MIMIC-IV: HR, 2.84; 95% CI, 2.08–3.87; P < 0.01).

[0136] Linear regression analysis showed a fairly positive correlation between NLR and CRP (R²=0.091, P<0.001) (part B of Figure 3). However, no significant correlation was found between NLR and UA levels (R²=8.9e-05, P=0.61) (part C of Figure 3), nor between CRP and UA (R²=0.0017, P=0.026) (part A of Figure 3). ROC curves were generated to compare the predictive ability of NLR, UA, and CRP for gout recurrence (part D of Figure 3). The AUC of NLR was 0.629, indicating better predictive performance compared to UA (AUC=0.591) and CRP (AUC=0.613). The DeLong test confirmed that NLR's predictive performance was significantly better than UA (P=0.025), while there was no significant difference between CRP and NLR (P=0.623).

[0137] Figure 4 shows a stratified analysis of the GoutRe and MIMIC-IV cohorts by age, sex, eGFR, UA level, and comorbidities. A significant association between elevated NLR and increased risk of gout recurrence was observed in all subgroups. For example, in the GoutRe cohort, the heart rate (HR) was 2.38 (95% CI, 1.80–3.15; P < 0.001) for patients with UA levels between 7 and 7.9 mg / dL, compared to 2.83 (95% CI, 2.08–3.84; P < 0.001) for patients with UA levels between 9 and 9.9 mg / dL.

[0138] In both the GoutRe and MIMIC-IV cohorts, elevated NLR remained a strong predictor of gout recurrence across various clinical settings and comorbidities, even after adjusting for all covariates. These trends were consistent across subgroups including cancer, cardiovascular disease, diabetes, dyslipidemia, hypertension, heart failure, kidney disease, stroke, thyroid disease, and kidney stones, as well as across age, sex, eGFR, and UA levels. Notably, in the MIMIC-IV cohort, the HR for gout recurrence in patients with thyroid disease was 5.16 (95% CI, 2.38–11.19; P < 0.001), further highlighting the strong predictive value of NLR across different patient populations (Figure 4).

[0139] Adding NLR to the baseline prediction model significantly improved the accuracy of predicting gout recurrence during hospitalization, with the C-statistic increasing from 0.65 to 0.68 in the GoutRe cohort (P < 0.001) and from 0.80 to 0.81 in the MIMIC-IV cohort (P = 0.003). A significant increase in the IDI index further supports these improvements. The ROC curve (Figure 5) visually demonstrates the improvement in sensitivity and specificity after incorporating NLR. Furthermore, decision curve analysis confirms the clinical applicability of the enhanced model, showing consistent net gains for both cohorts within the threshold probability range.

[0140] Four different modeling methods were used to evaluate the predictive performance of gout recurrence: Cox regression, support vector machine (SVM), random survival forest, and XGBoost. Including NLR significantly improved the AUC of all models on the GoutRe and MIMIC-IV datasets. Specifically, the XGBoost model showed the highest AUC, indicating its superior performance (GoutRe: AUC=0.73; MIMIC-IV: AUC=0.85), followed by the random survival forest model (GoutRe: AUC=0.72; MIMIC-IC-IV: ACC=0.85). This highlights the robustness of XGBoost and random survival forest models in predicting gout recurrence when incorporating NLR (Figure 5).

[0141] Given the lack of reliable predictors of gout recurrence, this study aims to bridge this gap by thoroughly investigating the potential association between non-recurring lung rate (NLR) and gout recurrence. To date, this is the first study conducted in hospitalized gout patients to assess the association between NLR and gout recurrence. Using data from the GoutRe cohort, including patients from five hospitals in China and the MIMIC-IV database, higher NLR levels were found to be independently associated with an increased risk of gout recurrence in the general population. This not only clearly validates the importance of NLR as a novel predictor of gout recurrence but also demonstrates its broad applicability across different patient populations, thus significantly improving the predictive power and accuracy of existing predictive models.

[0142] Based on a calculated cutoff value of 2.69, the patient population was precisely divided into two groups: a high NLR group and a low NLR group. Comparative analysis revealed that patients in the high NLR group had a significantly increased risk of gout recurrence compared to the low NLR group. These results are consistent with previous studies, indicating that patients with acute gout have an elevated percentage of neutrophils and a decreased percentage of lymphocytes in their peripheral blood. Furthermore, patients with acute gout have a higher NLR compared to patients in remission.

[0143] The predictive power of the neutrophil reflex (NLR) for gout recurrence stems from its reflection of systemic inflammatory status. The NLR is a direct and effective indicator for assessing the body's inflammatory response. Numerous studies have demonstrated the significant value of the NLR in disease assessment, prediction, and evaluation of disease activity and treatment efficacy in patients with systemic lupus erythematosus and rheumatoid arthritis complicated by lupus nephritis. Gout is an inflammatory disease whose recurrence is closely related to the level of systemic inflammation. During a gout attack, neutrophils migrate to the affected joints after urate crystal deposition and play a crucial role in eliminating these crystals through phagocytosis.

[0144] This process causes localized inflammation, leading to joint swelling and pain. Lymphocytes play a crucial role in immune system regulation, and their reduction may indicate impaired immune regulation and ineffective inflammatory suppression, thereby increasing the risk of gout recurrence. Given the sensitivity of a single cell type as an inflammatory marker to fluctuations caused by various internal and external factors, it may be insufficient to accurately describe the complex characteristics and severity of the immune-inflammatory state.

[0145] In contrast, NLR, obtained by integrating neutrophil and lymphocyte counts, can simultaneously reflect changes in the state of these two key inflammatory cells, revealing the body's inflammatory and immune status at a broader level. Therefore, the combined ratio of multiple cell counts as markers of inflammation may be more reliable and accurate than a single cell indicator. Thus, an elevated NLR value indicates an increased level of inflammation in the patient, which implies an increased likelihood of future relapses.

[0146] Compared to previous predictors of gout recurrence, the gout recurrence model developed in this study showed significant performance improvements, with a higher AUC. This research represents a major breakthrough and in-depth exploration across multiple dimensions.

[0147] Comprehensive validation was conducted to confirm the broad applicability of NLR. Although uric acid levels are the primary determinant of gout attacks, some patients with normal uric acid levels may still experience recurrent attacks, suggesting that relying solely on uric acid levels as a predictive indicator may lack sufficient accuracy. Tophus is a manifestation of chronic gout caused by recurrent and long-term attacks, indicating that the disease has progressed to a chronic stage.

[0148] However, it should be noted that not all gout patients will develop tophi. Uric acid-lowering medications can effectively reduce uric acid levels, but the timeliness of treatment and patient adherence can affect their effectiveness. Furthermore, gout attacks can still occur even with medication. Considering these factors, accurately predicting gout recurrence in patients with normal uric acid levels, no tophi formation, and who are receiving uric acid-lowering treatment is more challenging.

[0149] Subgroup analysis showed that NLR had consistent and robust predictive power across different patient populations, particularly in individuals with normal serum uric acid levels, no tophi, and receiving uric acid-lowering therapy. This finding suggests that NLR may partially compensate for the limitations of traditional predictors in predicting gout recurrence, providing a new perspective and tool for gout prediction. It is proposed that due to the inflammatory nature of gout, mild local or systemic inflammation may persist even in patients with normal serum uric acid levels and no tophi. NLR can sensitively capture this underlying inflammatory activity, leading to elevated NLR levels.

[0150] The predictive efficacy of the NLR in patients receiving uric acid-lowering therapy may be partly attributed to its ability to identify unresponsive individuals or those with other persistent inflammatory factors. As a comprehensive inflammatory marker, the NLR may more comprehensively reflect the impact of population heterogeneity in gout on disease progression and recurrence risk. Therefore, the NLR shows relatively stable predictive efficacy across different patient populations. As an independent composite prognostic factor, the predictive efficacy of the NLR is less affected by common clinical variables, indicating that it provides supplementary information beyond traditional indicators and contributes to a comprehensive risk assessment of patient recurrence.

[0151] Furthermore, the incremental impact of incorporating NLR into each constructed machine learning model was evaluated. The analysis revealed a significant finding: incorporating NLR significantly improved the accuracy of predicting gout recurrence, thus highlighting the independent and critical predictive value of NLR.

[0152] Finally, a comparative analysis of the sensitivity and specificity of NLR, CRP, and UA in predicting gout recurrence revealed that NLR had a higher AUC than CRP and UA. A study explored the efficacy of various inflammatory markers in the diagnosis of acute gout, showing that CRP was superior to other inflammatory markers such as SIRI, ESR, NLR, MLR, SII, and PLR.

[0153] However, this study showed that NLR was superior to CRP in predicting gout recurrence. This may be because NLR, as an indicator of the overall state of the body's immune system, is more sensitive to monitoring the dynamic fluctuations in cytokine release and inflammatory responses. Furthermore, NLR may be more closely related to the pathophysiological mechanisms of gout, especially considering the crucial role of neutrophils in gout attacks. CRP is an acute-phase inflammatory biomarker synthesized by the liver in response to immune cytokine stimulation.

[0154] Although it shows a rapid increase in inflammatory infections and other conditions, its ability to accurately reflect the degree of inflammation often exhibits a time lag, making it susceptible to various non-infectious factors. Consistent with previous studies, GlycA has been shown to serve as a reliable long-term biomarker for assessing neutrophil hyperactivity, and it is a stronger predictor of gout recurrence compared to UA levels. While several studies have shown a strong association between UA levels and the risk of gout recurrence, capturing the body's overall inflammatory response solely through direct indicators of uric acid metabolism remains challenging. Although hyperuricemia is a prerequisite for gout attacks, not all patients with hyperuricemia will develop gout; some gout patients may exhibit normal serum uric acid levels during an attack.

[0155] Therefore, the predictive value of UA levels in determining gout recurrence has certain limitations. NLR, as a novel inflammatory marker, exhibits higher sensitivity and specificity than CRP and UA levels in predicting the risk of gout recurrence. By integrating information from neutrophils and lymphocytes, it can more comprehensively reflect the body's inflammatory response, thus providing a more reliable basis for assessing the recurrence risk in gout patients.

[0156] This study contributes by validating NLR as a cost-effective, readily available, and simple biomarker for predicting gout recurrence. This finding provides a more precise basis for clinical decision-making and helps healthcare providers develop personalized prevention and treatment strategies, including adjusting medication regimens and enhancing lifestyle interventions. The ultimate goal is to effectively reduce the risk of gout recurrence in patients.

[0157] This study has some limitations. First, the analysis primarily focused on comparing NLR, CRP, and UA, without a comprehensive evaluation of other inflammatory biomarkers. Future research should include a wider range of inflammatory biomarkers to provide more in-depth comparative analyses. Second, due to the dynamic nature of NLR as a biomarker influenced by multiple factors, a single measurement may not adequately reflect an individual's true risk level. Therefore, future research should expand the sample size to improve the generalizability of the findings and incorporate additional inflammatory biomarkers and other relevant indicators to further improve the predictive performance of the model. Furthermore, the study was limited to hospitalized patients, which may affect the broad applicability of the results. Future research should include a more diverse patient population to validate the generalizability of the conclusions.

[0158] The findings strongly support NLR as a practical and sensitive biomarker for predicting gout recurrence. Incorporating NLR into clinical practice can help clinicians accurately identify high-risk patients for gout recurrence, improve risk stratification and management of gout patients, help develop more personalized prevention strategies and optimize treatment interventions, ultimately reducing the risk of recurrence.

[0159] In this international, multicenter, retrospective cohort study of 7,603 hospitalized patients with gout, higher non-recurring risk (NLR) (cutoff >2.69) was significantly associated with an increased risk of gout recurrence across various clinical settings and comorbidities. Incorporating NLR into predictive models significantly improved their performance. Compared to allergic urea (UA) and cyclophosphamide (CRP), NLR demonstrated superior predictive ability. In this study, NLR proved to be a simple, reliable, and accessible biomarker for identifying patients at high risk of gout recurrence, potentially improving clinical management and guiding tailored treatment interventions.

[0160] Figure 6 is a schematic diagram of a gout recurrence risk assessment system module based on the neutrophil-to-lymphocyte ratio provided in an embodiment of this application. In this embodiment, the system includes:

[0161] The data acquisition module 11 is used to collect electronic medical record data, clinical pathology data, hospitalization and clinical follow-up data of the same target population within a preset time period from the data center system.

[0162] The data processing module 12 is used to preprocess the electronic medical record data, clinical pathology data, hospitalization and clinical follow-up data, and generate gout recurrence risk assessment sample data through data standardization processing.

[0163] NLR assessment module 13 is used to establish a joint model of Cox proportional hazards regression model and competing hazard model to assess the association between neutrophil to lymphocyte ratio (NLR) and gout recurrence.

[0164] The model building module 14 is used to add NLR as a prognostic factor for gout recurrence risk to the baseline model when the assessment judgment conditions are met, so as to build a variety of candidate prediction models for gout recurrence risk.

[0165] The model selection module 15 is used to evaluate the predictive effect of the various candidate models for gout recurrence risk using the C-statistic, the net reclassification index (NRI), and the comprehensive discriminant improvement index (IDI) to obtain the target gout recurrence risk assessment model.

[0166] The risk assessment module 16 is used to predict the risk of gout recurrence in patients based on their clinical data and the target gout recurrence risk assessment model, and to generate corresponding risk assessment results.

[0167] The comparison display module 17 is used to construct a visualization interface and display the evaluation of the optimal threshold and predictive value of the neutrophil-to-lymphocyte ratio (NLR) for gout recurrence, and compare its efficacy with traditional biomarkers.

[0168] It is understood that the gout recurrence risk assessment system based on the neutrophil-to-lymphocyte ratio provided in this application can effectively address the problems of incomplete and skewed distribution of clinical data, improve the quality and stability of data, improve the accuracy of assessment and prediction by screening out effective target gout recurrence risk assessment models, and provide reliable auxiliary decision support for clinicians.

[0169] Referring to Figure 7, which illustrates an electronic terminal device according to an embodiment of this application, the electronic terminal device shown in Figure 7 includes at least the following components: one or more processors, one or more input devices, one or more output devices, and one or more memories. The processor, input devices, output devices, and memories communicate with each other via a communication bus. The memory stores computer programs, including program instructions. The processor executes the program instructions stored in the memory. The processor is configured to invoke the program instructions to perform the functions of the modules / units in the above-described device embodiments, such as the function of the module shown in Figure 6.

[0170] In embodiments of this application, a computer-readable storage medium includes instructions that instruct a device to perform a system as described in the first aspect. For example, the instructions instruct the device to perform a method and system for assessing the risk of gout recurrence based on the neutrophil-to-lymphocyte ratio, as shown in the steps of FIG1.

[0171] It should be understood that, in the embodiments of the present invention, the processor may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor. It should be noted that a part of the electronic device described above can also be implemented using a computer. In this case, the program for implementing the control function can be recorded on a computer-readable recording medium, and the program recorded on the recording medium can be read into the computer and executed.

[0172] Input devices may include touchpads, fingerprint sensors (for collecting the user's fingerprint information and fingerprint orientation information), microphones, etc., while output devices may include displays (LCDs, etc.), speakers, etc.

[0173] It should be noted that the term "computer" as used here refers to a computer built into an electronic device, employing hardware including an operating system and peripheral devices. Furthermore, "computer-readable recording media" refers to removable media such as floppy disks, magneto-optical disks, ROMs, and CD-ROMs, as well as storage devices such as hard drives built into a computer.

[0174] Furthermore, a "computer-readable recording medium" can include: a medium that dynamically stores a program for a short period of time, such as a communication line used when transmitting a program via a network such as the Internet or a communication line such as a telephone line; or a medium that stores a program for a fixed period of time, such as volatile memory inside a computer that serves as a server or client in this case. In addition, the aforementioned program can be a program used to implement the above-mentioned functions, or it can be a program that can implement the above-mentioned functions by combining with programs already recorded in the computer.

[0175] Furthermore, the electronic device in the above embodiments can also be implemented as an assembly (device group) composed of multiple devices. Each device constituting the device group can possess some or all of the functions or functional blocks of the electronic device in the above embodiments. As a device group, it is sufficient to have all the functions or functional blocks of the electronic device.

[0176] Those skilled in the art should recognize that the above embodiments are only used to illustrate this application and are not intended to limit this application. Any appropriate changes and variations made to the above embodiments within the essential spirit and scope of this application fall within the scope of protection claimed in this application.

Claims

1. A method for assessing the risk of gout recurrence based on the ratio of neutrophils to lymphocytes, characterized in that, The method includes: S1, collecting electronic medical record data, clinical pathology data, and hospitalization and clinical follow-up data of the same target population within a preset time period from a data center system; S2, preprocessing the electronic medical record data, clinical pathology data, and hospitalization and clinical follow-up data, and generating gout recurrence risk assessment sample data through data standardization; S3, establishing a joint model of Cox proportional hazards regression model and competing risk model to assess the association between the neutrophil-to-lymphocyte ratio (NLR) and gout recurrence; S4, when the association assessment criteria are met, adding NLR as a characteristic variable of the prognostic factor for gout recurrence risk to the baseline model to construct multiple candidate prediction models for gout recurrence risk; S5, using the C-statistic, net reclassification index (NRI), and comprehensive discriminant improvement index (IDI) to assess... The aforementioned multiple candidate prediction models for gout recurrence risk are used to evaluate the predictive effect of gout recurrence in order to obtain a target gout recurrence risk assessment model; S6, based on the patient's clinical data and the target gout recurrence risk assessment model, the patient's gout recurrence risk is predicted, and the corresponding risk assessment results are generated; S7, a visualization interface is constructed and displayed to evaluate the optimal threshold and predictive value of the neutrophil-to-lymphocyte ratio (NLR) for gout recurrence, and its efficacy is compared with traditional biomarkers; wherein, S3, a Cox proportional hazards regression model and a competing risk model are established to evaluate the association between the neutrophil-to-lymphocyte ratio (NLR) and gout recurrence, including: S3.1, using the Lasso method to screen out the variables with the greatest influence on the model, including: the goal of the Lasso method is to minimize the following loss function: ,in, It is the first The target value of each observation. It is the first The first observation One characteristic, It is the intercept term. It is the first The regression characteristic coefficients of each feature, These are regularization parameters that control the strength of regularization. It is the sample size. It is the number of features, and the L1 regularization term. This allows some coefficients to be compressed to zero, thereby achieving feature selection and obtaining the dataset. S3.2, Substitute the filtered data into the Cox proportional hazards regression model to obtain the regression characteristic coefficients. Among them, the estimator satisfy: ,in, This represents the sample composition of the Cox model. ， Indicates the first A period of survival, Indicates the time of deletion. Represents the event identifier vector; S3.3, using regression feature coefficients For dataset Through formula Transformation to obtain a new dataset S3.4, Divide the new dataset into training and validation sets according to a preset ratio; S3.5, Train the competing risk model using the training set and evaluate it using the validation set to obtain the competing risk model; S3.6, Determine the optimal cutoff value for NLR using the Grey test statistic maximization method in the competing risk model and the log-rank test statistic maximization method in the Cox proportional hazards survival model, and conduct sensitivity analysis using the competing risk model and Kaplan-Meier survival analysis to confirm the robustness of the research results under different model settings.

2. The method for assessing the risk of gout recurrence based on the neutrophil-to-lymphocyte ratio according to claim 1, characterized in that, In step S1, the same target population is a set of hospitalized patients with gout symptoms, ranging from those without gout symptoms to those with gout symptoms. The electronic medical record data includes: neutrophil-to-lymphocyte ratio (NLR), gout recurrence time, recurrence status, and covariates. The covariates include: demographic characteristics, lifestyle factors, laboratory tests, physical examinations, comorbidities, and medication use.

3. The method for assessing the risk of gout recurrence based on the neutrophil-to-lymphocyte ratio according to claim 1, characterized in that, S2 involves preprocessing the electronic medical record data, clinical pathology data, hospitalization and clinical follow-up data, and generating gout recurrence risk assessment sample data through data standardization. This includes: viewing outliers using box plots and removing outliers using IQR rules; visualizing the distribution of missing data and performing imputation; and standardizing the imputed data using the following formula: ,in The original data, The average of the raw data, The standard deviation of the original data is given. Statistical analysis is performed on the standardized data. The Shapiro-Wilk test is used to assess the normality of continuous variables. Independent t-tests or nonparametric tests are used to compare continuous variables among different NLR groups. Categorical variables are analyzed using chi-square tests or Fisher's exact tests. Missing data are processed using the chain equation multiple imputation method (MICE) combined with the classification and regression tree (CART) method. The results of each imputation dataset are then combined to obtain the final estimate.

4. The method for assessing the risk of gout recurrence based on the neutrophil-to-lymphocyte ratio according to claim 3, characterized in that, In step S4, when the association judgment condition is met, NLR is added as a characteristic variable of the prognostic factor for gout recurrence risk to the baseline model to construct multiple candidate prediction models for gout recurrence risk. The association judgment condition is to determine whether the neutrophil-to-lymphocyte ratio (NLR) is associated with an increased risk of gout recurrence during hospitalization, and whether it improves the prediction accuracy compared with traditional markers such as serum uric acid (UA) level, tophi, and C-reactive protein (CRP).

5. The method for assessing the risk of gout recurrence based on the neutrophil-to-lymphocyte ratio according to claim 4, characterized in that, S5 involves evaluating the predictive performance of various candidate models for gout recurrence risk using the C-statistic, Net Reclassification Index (NRI), and Integrated Discriminant Improvement Index (IDI) to obtain a target gout recurrence risk assessment model. This includes: constructing various candidate models for gout recurrence risk, including at least Cox regression, Support Vector Machine (SVM), k-Nearest Neighbors (KNN), Random Survival Forest (RSF), and XGBoost; evaluating the incremental predictive performance of NLR using the C-statistic, NRI, and IDI, and comparing them to perform a coarse screening of the candidate models; generating ROC curves for each candidate model and calculating the area under the curve (AUC) to assess predictive accuracy; comparing the differences between AUCs using the DeLong test; obtaining the best-performing candidate model as the target gout recurrence risk assessment model; calculating the NRI and IDI to evaluate the incremental predictive value of incorporating NLR into the baseline model, and obtaining confidence intervals through guided resampling to optimize the target gout recurrence risk assessment model.

6. The method for assessing the risk of gout recurrence based on the neutrophil-to-lymphocyte ratio according to claim 5, characterized in that, S6, based on the patient's clinical data and the target gout recurrence risk assessment model, predicts the patient's risk of gout recurrence and generates corresponding risk assessment results, including: inputting the patient's clinical data into the target gout recurrence risk assessment model; and outputting potential risk assessment results.

7. A gout recurrence risk assessment system based on the neutrophil-to-lymphocyte ratio, applied to the gout recurrence risk assessment method based on the neutrophil-to-lymphocyte ratio as described in any one of claims 1 to 6, characterized in that, The system includes: a data acquisition module for collecting electronic medical record data, clinical pathology data, and hospitalization and clinical follow-up data of the same target population within a preset time period from a data center system; a data processing module for preprocessing the electronic medical record data, clinical pathology data, and hospitalization and clinical follow-up data, and generating gout recurrence risk assessment sample data through data standardization; an NLR assessment module for establishing a joint model of a Cox proportional hazards regression model and a competing risk model to assess the association between the neutrophil-to-lymphocyte ratio (NLR) and gout recurrence; and a model construction module for adding NLR as a prognostic factor characteristic variable for gout recurrence risk when the assessment criteria are met. The system employs a baseline model to construct multiple candidate predictive models for gout recurrence risk. A model selection module evaluates these candidate models using the C-statistic, Net Reclassification Index (NRI), and Integrated Discriminant Improvement Index (IDI) to assess their predictive effectiveness in assessing gout recurrence risk, thereby obtaining a target gout recurrence risk assessment model. A risk assessment module predicts the patient's gout recurrence risk based on clinical data and the target model, generating corresponding risk assessment results. A comparison and display module constructs a visual interface to assess the optimal threshold and predictive value of the neutrophil-to-lymphocyte ratio (NLR) for gout recurrence, comparing its efficacy with traditional biomarkers.

8. An electronic device, characterized in that, include: processor; A memory for storing processor-executable instructions; wherein the processor is configured to implement, when executing the instructions, a method for assessing the risk of gout recurrence based on the neutrophil-to-lymphocyte ratio as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program that instructs the device to perform a gout recurrence risk assessment method based on the neutrophil-to-lymphocyte ratio as described in any one of claims 1 to 6.

Images