Predicting Postoperative Sepsis Risk in Diabetic Urolithiasis Patients: A Multimodal Clinical Data-Driven Machine Learning Model

Predicting Postoperative Sepsis Risk in Diabetic Urolithiasis Patients: A Multimodal Clinical Data-Driven Machine Learning Model | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Predicting Postoperative Sepsis Risk in Diabetic Urolithiasis Patients: A Multimodal Clinical Data-Driven Machine Learning Model Dianyu Wang, Dongwei Pan, Zuheng Wang, Zequn Su, Junhao Mi, Mingda Wang, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7584146/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 9 You are reading this latest preprint version Abstract Objective Diabetic patients are more prone to urinary tract infections due to metabolic abnormalities and impaired immune function, which can progress to urosepsis. This study aims to construct and validate an efficient and accurate predictive model, based on multimodal clinical data combined with machine learning techniques, to early assess the risk of postoperative infectious urosepsis in diabetic patients with urinary stones, thereby providing support for clinical decision-making. Methods 532 patients diagnosed with diabetes who underwent surgical treatment for upper urinary tract stones was included. The patients were randomly divided into training (70%) and validation (30%) cohorts. A total of 164 multimodal clinical parameters were included, and those with statistically significant differences ( P < 0.05) were selected. Feature selection was performed using LASSO regression and the Boruta algorithm. Nine machine learning (ML) algorithms were explored to predict the risk of postoperative infectious urosepsis in diabetic patients with urinary stones. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), learning curve, calibration curve, and decision curve analysis (DCA). The contribution of key predictive factors was visualized using the SHAP method. Results Among the 164 multimodal clinical parameters, 59 were significantly associated with the occurrence of postoperative infectious urosepsis. After feature selection, four key parameters were identified: p_IL_6, p_PCTp_ALB, p_T, and p_HR. Among the nine ML algorithms, logistic regression exhibited the best predictive ability. The AUC in the validation cohort was 0.903. The learning curve indicated good and stable model fitting, while the calibration curve demonstrated a high degree of agreement between predicted and actual probabilities. The decision curve analysis revealed that the model provided significant clinical net benefit within a threshold range of 5% to 90%. Conclusion The model constructed using logistic regression performed excellently in predicting the risk of postoperative infectious urosepsis in diabetic patients with urinary stones and can help clinicians better identify high-risk patients. Further prospective validation in multicenter studies is needed to confirm the model's generalizability. Diabetes upper urinary tract stones urosepsis machine learning risk prediction model Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Introduction Infectious urosepsis is one of the most severe complications after surgery for urinary tract stone patients. Its rapid progression is often associated with high mortality rates and substantial medical costs, making it a central challenge in perioperative management. Diabetic patients, due to metabolic abnormalities and impaired immune function, are more susceptible to urinary tract infections (UTI), which can then progress to urosepsis[1]. Studies have shown[2] that in type 2 diabetic patients with upper urinary tract stones (UUTS), the incidence of urosepsis is 4.5%, with diabetes patients accounting for 34.8% of these cases. It is worth noting that in diabetic patients, the risk of postoperative infectious complications significantly increases after undergoing surgical treatments such as percutaneous nephrolithotomy (PCNL) or ureteroscopy (URSL)[3–5]. Moreover, once diabetic patients develop urosepsis, their condition is more likely to deteriorate into septic shock, particularly in elderly patients[6]. However, despite the significantly increased risk of postoperative infection in diabetic patients with urinary stones, effective predictive tools for this high-risk group are still lacking. Traditional assessment methods often rely on single indicators or clinical experience[7], which makes it difficult to accurately capture the complex metabolic and immune status of diabetic patients. Existing risk scoring systems such as qSOFA, SIRS, and NEWS have lower sensitivity in this population, making them prone to missing high-risk individuals[8]. Therefore, there is an urgent need to explore more accurate predictive methods for postoperative infectious urosepsis risk in diabetic patients with urinary stones, in order to develop more personalized and precise treatment strategies, ultimately improving the patients' quality of life and survival rate. In recent years, machine learning (ML) has not only been able to autonomously identify new variables and their complex relationships from datasets[9], but also explain model decision logic through techniques like SHAP values[10], thus improving prediction credibility and clinical applicability. Its application in the medical field has rapidly expanded, showing great promise and is increasingly used in developing novel prognostic models for various diseases. In summary, this study aims to comprehensively analyze the multimodal clinical data of diabetic patients with urinary stones, identify significant predictive factors for postoperative infectious urosepsis risk, and develop and validate an ML prediction model using advanced ML techniques. This will provide a theoretical basis and decision support for early identification and precise intervention, promoting the establishment of individualized perioperative management strategies and improving patient prognosis. Materials and Methods This study included 532 patients who were diagnosed with diabetes and underwent surgical treatment for upper urinary tract stones at the Sixth Affiliated Hospital of Guangxi Medical University between June 2018 and June 2023. The study was conducted in strict accordance with the ethical principles outlined in the Declaration of Helsinki, and all data were derived from real clinical cases. Informed consent was obtained from each patient or their authorized representative prior to sample collection. Inclusion criteria were as follows: (1) patients with a prior diagnosis of diabetes who were subsequently diagnosed with upper urinary tract stones at the Sixth Affiliated Hospital of Guangxi Medical University; (2) patients who received surgical treatment in accordance with the indications for surgical management of urinary stone disease as outlined in the 2015 European Association of Urology (EAU) Guidelines for Urolithiasis; (3) complete demographic and clinical examination data available; (4) age ≥ 18 years. Exclusion criteria included: (1) patients with an unclear diagnosis or without a history of diabetes; (2) patients with concomitant urinary system malformations; (3) patients with other systemic infectious diseases; (4) patients with malignant tumors; (5) patients with mental health disorders or impaired speech and communication abilities. Clinical Data Collection and Feature Selection The dataset used in this study comprises 532 cases of patients previously diagnosed with diabetes who underwent surgical treatment for upper urinary tract stones. It includes 164 feature variables, categorized as follows: (1) Demographic and vital sign data, including age, gender, BMI, heart rate, blood pressure, body temperature, etc.; (2) Inflammatory and infection markers, including CRP, PCT, IL-6, SAA, and urinary white blood cells; (3) Surgical-related information, including surgical methods, number of surgeries, ASA classification, and Barthel index; (4) Routine laboratory tests, including blood and urine tests, liver and kidney function, and coagulation function. To reduce the number of features to be tested across various classifiers, feature selection was performed. Initially, parameters with no significant differences between the two groups were excluded. Subsequently, feature selection was carried out using Lasso regression and the Boruta algorithm. Lasso regression is a statistical modeling method that combines variable selection with regularization, making it particularly suitable for high-dimensional data analysis. The Boruta algorithm, based on random forests, is particularly effective for identifying all relevant features associated with the target variable in high-dimensional data. In this study, Lasso regression and the Boruta algorithm were combined, with the intersection of the selected features from both methods used for final feature selection. This approach not only preserves predictive and relevant features but also avoids overlooking important nonlinear or interaction features. It provides a more stable, accurate, and interpretable feature set, while reducing the risk of overfitting. The selected features were then used for subsequent model training and analysis. Study Design The workflow of this study is briefly summarized in a flowchart, and the study cohort is systematically described(Figs. 1 ). Specifically, the data collected from the Sixth Affiliated Hospital of Guangxi Medical University were randomly divided into a training set (n = 372, 70%) and a validation set (n = 160, 30%). After feature selection, nine machine learning algorithms (ML) were used to construct the model in the training cohort based on 10-fold cross-validation, including logistic regression, extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), random forest (RF), adaptive boosting (AdaBoost), gradient boosting decision tree (GBDT), Gaussian naive Bayes (GNB), support vector machine (SVM), and K-nearest neighbors (KNN). These models were then evaluated for performance in the validation cohort. The models were comprehensively assessed, and the classifier with the best predictive performance was selected to build the final risk prediction model. Model evaluation metrics included accuracy, positive predictive value (PPV), negative predictive value (NPV), and others. Additionally, the model’s ability to predict the risk of postoperative infectious urosepsis was tested using receiver operating characteristic (ROC) curves, learning curves, calibration curves, and decision curve analysis (DCA). Finally, SHAP (SHapley Additive exPlanations) values were used to visualize the impact of key variables on the model's output, enhancing model interpretability and clinical applicability. Statistical Analysis All data were analyzed using Python software (version 3.8), utilizing the glmnet (version 4.1), xgboost (version 2.0.1), lightgbm (version 3.2.1), and scikit-learn (version 1.1.3) packages. Normality tests were performed for quantitative data. Data that followed a normal distribution were expressed as mean ± standard deviation and analyzed using the Student’s t-test. Data that did not follow a normal distribution were expressed as median and interquartile range (IQR) and analyzed using the Mann-Whitney U test. Categorical data were expressed as counts and percentages and analyzed using the chi-square test. All statistical tests were two-sided, with P values < 0.05 considered statistically significant. Results Patient Feature Selection According to the inclusion criteria, 532 patients who were previously diagnosed with diabetes and underwent surgical treatment for upper urinary tract stones were finally included. These patients were randomly divided into a training cohort (n = 372) and a validation cohort (n = 160), with a ratio of 7:3. Among the 164 parameters, 59 were significantly associated with the occurrence of postoperative infectious urosepsis (P < 0.05) (Table 1 ). Next, feature selection was performed using Lasso regression and the Boruta algorithm[11]. Lasso regression selected variables with non-zero coefficients (β ≠ 0), resulting in 5 features that met the criteria (Figs. 2 A-B), including p_IL_6, p_TP, p_PCT/p_ALB, p_T, and p_HR. The Boruta algorithm selected "importance scores" for each true feature that were significantly higher than all shadow features' Confirmed and Tentative indicators (yellow and green areas in the figure). A total of 16 features met the criteria (Fig. 2 C), including p_GGT, p_SAA, p_Lymph_WBC, p_Lymph, p_ALB, p_NLR, p_PLR, p_NLPR, p_SII, p_LCR, p_CRP/p_ALB, p_IL_6, p_PCT/p_ALB, p_T, p_HR, and p_procalcitonin. Table 1 Biomarker Characteristics of Patients with non - sepsis and Sepsis Variables non - sepsis (N = 478) sepsis (N = 54) p Age, Median [Q1-Q3] 58.00 [54.00;67.00] 58.00 [53.00;64.75] 0.427 BMI, Mean (SD) 24.37 (2.99) 23.41 (3.21) 0.039 times_operstion, Median [Q1-Q3] 2.00 [1.00;3.00] 2.00 [1.00;3.00] 0.838 T, Median [Q1-Q3] 36.60 [36.50;36.70] 36.60 [36.30;36.70] 0.912 HR, Median [Q1-Q3] 73.00 [63.00;85.00] 85.00 [71.00;97.00] < 0.001 SBP, Median [Q1-Q3] 132.00 [123.00;145.00] 124.00 [119.00;141.00] 0.02 DBP, Median [Q1-Q3] 82.00 [76.00;89.00] 79.00 [75.00;88.00] 0.202 SG, Median [Q1-Q3] 1.01 [1.00;1.01] 1.01 [1.00;1.01] 0.764 PH_value, Median [Q1-Q3] 6.00 [5.62;6.50] 6.00 [5.50;7.00] 0.836 SED_RBC, Median [Q1-Q3] 95.00 [12.00;1670.25] 62.50 [10.25;297.75] 0.076 SED_WBC, Median [Q1-Q3] 54.00 [17.08;221.00] 217.50 [45.50;420.12] 0.006 SED_EC, Median [Q1-Q3] 5.00 [2.00;12.00] 4.00 [2.00;10.75] 0.237 SED_casts, Median [Q1-Q3] 0.00 [0.00;1.00] 0.00 [0.00;1.00] 0.616 SED_bacteria, Median [Q1-Q3] 24.00 [9.00;81.75] 34.50 [15.50;202.25] 0.119 U_conductivity, Median [Q1-Q3] 11.65 [8.60;14.60] 10.60 [8.00;14.45] 0.352 WBC, Median [Q1-Q3] 7.01 [6.02;8.43] 6.88 [5.81;8.89] 0.974 Neut_WBC, Median [Q1-Q3] 61.25 [55.60;67.20] 61.40 [56.70;68.15] 0.457 Lymph_WBC, Mean (SD) 27.23 (8.26) 26.11 (7.89) 0.328 Mono_WBC, Median [Q1-Q3] 6.60 [5.60;8.00] 7.00 [5.25;7.97] 0.808 Eos_WBC, Median [Q1-Q3] 3.00 [2.00;4.70] 3.35 [2.20;4.57] 0.667 Baso_WBC, Median [Q1-Q3] 0.60 [0.40;0.80] 0.60 [0.50;0.80] 0.341 Neut, Median [Q1-Q3] 4.26 [3.43;5.34] 4.23 [3.43;5.95] 0.664 Lymph, Median [Q1-Q3] 1.88 [1.47;2.28] 1.83 [1.44;2.13] 0.289 Mono, Median [Q1-Q3] 0.46 [0.37;0.60] 0.48 [0.34;0.60] 0.908 Eos, Median [Q1-Q3] 0.21 [0.13;0.32] 0.20 [0.15;0.29] 0.876 Baso, Median [Q1-Q3] 0.04 [0.03;0.06] 0.04 [0.03;0.07] 0.484 RBC, Median [Q1-Q3] 4.42 [4.00;4.86] 4.21 [3.89;4.60] 0.062 HGB, Mean (SD) 124.67 (19.62) 115.83 (18.25) 0.001 HCT, Median [Q1-Q3] 0.38 [0.34;0.41] 0.35 [0.32;0.39] 0.002 MCV, Median [Q1-Q3] 87.40 [82.90;90.38] 87.05 [83.08;89.80] 0.366 MCH, Median [Q1-Q3] 29.10 [27.30;30.30] 28.90 [26.05;29.67] 0.135 MCHC, Median [Q1-Q3] 330.70 [321.00;340.00] 328.00 [316.25;336.75] 0.051 RDW, Median [Q1-Q3] 12.80 [12.20;13.70] 13.05 [12.43;13.88] 0.126 PLT, Median [Q1-Q3] 261.00 [216.00;312.00] 292.00 [240.00;330.75] 0.037 MPV, Median [Q1-Q3] 9.70 [9.30;10.20] 9.45 [9.20;10.10] 0.105 B_PCT, Median [Q1-Q3] 0.25 [0.21;0.30] 0.28 [0.24;0.31] 0.063 BUA, Median [Q1-Q3] 367.75 [292.88;438.75] 345.50 [287.25;428.70] 0.306 BUN, Median [Q1-Q3] 5.88 [4.67;7.69] 5.43 [4.26;8.05] 0.268 Scr, Median [Q1-Q3] 103.75 [81.52;135.98] 102.00 [80.25;134.75] 0.803 eGFR, Median [Q1-Q3] 66.81 [47.52;85.77] 64.50 [49.96;81.22] 0.962 HCO3, Median [Q1-Q3] 23.50 [21.80;25.10] 22.85 [20.68;24.54] 0.139 beta2_MG, Median [Q1-Q3] 2.57 [2.05;3.53] 2.83 [2.31;4.34] 0.043 CysC, Median [Q1-Q3] 1.20 [1.05;1.56] 1.27 [1.05;1.60] 0.446 TP, Median [Q1-Q3] 70.90 [67.80;74.20] 71.30 [68.93;76.68] 0.21 ALB, Median [Q1-Q3] 39.90 [37.80;42.00] 38.80 [36.05;41.30] 0.029 GLB, Median [Q1-Q3] 30.70 [27.90;34.53] 33.65 [29.15;37.60] 0.004 ALB_GLB, Median [Q1-Q3] 1.30 [1.10;1.50] 1.20 [1.00;1.30] 0.001 BIL, Median [Q1-Q3] 7.10 [5.20;9.47] 6.80 [5.20;10.83] 0.794 DBIL, Median [Q1-Q3] 3.30 [2.60;4.35] 3.35 [2.60;4.77] 0.498 I_Bil, Median [Q1-Q3] 3.70 [2.50;5.20] 3.70 [2.40;5.80] 0.926 GPT, Median [Q1-Q3] 15.00 [11.00;21.00] 16.00 [10.10;23.50] 0.894 GOT, Median [Q1-Q3] 16.70 [13.22;20.00] 15.95 [13.03;23.50] 0.606 ALP, Median [Q1-Q3] 71.00 [60.00;85.00] 75.50 [61.25;89.75] 0.299 GGT, Median [Q1-Q3] 27.00 [18.00;38.00] 29.50 [19.00;43.00] 0.37 TBA, Median [Q1-Q3] 4.25 [2.60;6.80] 3.70 [2.00;7.08] 0.398 CRP, Median [Q1-Q3] 3.01 [1.39;7.84] 3.90 [2.42;11.29] 0.04 K, Median [Q1-Q3] 3.91 [3.64;4.17] 3.97 [3.70;4.25] 0.272 Ca, Median [Q1-Q3] 2.30 [2.23;2.37] 2.30 [2.22;2.37] 0.981 PT, Median [Q1-Q3] 10.90 [10.41;11.60] 10.95 [10.66;12.00] 0.103 INR, Median [Q1-Q3] 0.95 [0.90;1.01] 0.95 [0.92;1.05] 0.095 PTA, Median [Q1-Q3] 115.50 [101.25;128.00] 111.50 [91.50;123.00] 0.043 TT, Median [Q1-Q3] 18.60 [17.90;19.40] 18.60 [17.45;19.55] 0.455 APTT, Median [Q1-Q3] 25.70 [23.50;28.37] 26.07 [23.50;28.35] 0.426 PF, Median [Q1-Q3] 3.36 [2.90;4.22] 3.54 [2.93;4.90] 0.106 NLR, Median [Q1-Q3] 2.22 [1.71;3.06] 2.29 [1.73;3.19] 0.467 PLR, Median [Q1-Q3] 134.93 [107.96;180.56] 155.05 [121.07;206.97] 0.016 LMR, Median [Q1-Q3] 4.13 [3.08;5.24] 3.87 [2.89;4.99] 0.42 ELR, Median [Q1-Q3] 0.11 [0.07;0.18] 0.12 [0.08;0.18] 0.36 dNLR, Median [Q1-Q3] 1.58 [1.26;2.06] 1.58 [1.31;2.14] 0.472 NLPR, Median [Q1-Q3] 0.01 [0.01;0.01] 0.01 [0.01;0.01] 0.59 SII, Median [Q1-Q3] 580.54 [409.60;829.07] 696.80 [436.47;1022.01] 0.101 AISI, Median [Q1-Q3] 274.11 [168.97;458.34] 276.18 [203.48;557.52] 0.287 SIRI, Median [Q1-Q3] 1.01 [0.68;1.67] 1.00 [0.79;1.92] 0.678 LCR, Median [Q1-Q3] 0.66 [0.25;1.42] 0.42 [0.18;0.84] 0.028 CRP_ALB, Median [Q1-Q3] 0.08 [0.03;0.20] 0.10 [0.06;0.32] 0.031 p_CRP, Median [Q1-Q3] 3.07 [0.86;8.22] 21.98 [2.31;53.80] < 0.001 p_SAA, Median [Q1-Q3] 10.00 [6.00;20.00] 23.00 [10.00;72.00] 0.001 p_procalcitonin, Median [Q1-Q3] 0.05 [0.03;0.08] 0.41 [0.09;14.23] < 0.001 p_IL_6, Median [Q1-Q3] 14.65 [7.70;32.80] 71.35 [27.74;419.10] < 0.001 p_WBC, Median [Q1-Q3] 7.92 [6.36;9.98] 10.37 [6.31;13.36] 0.01 p_Neut_WBC, Median [Q1-Q3] 69.50 [61.50;78.47] 79.55 [66.45;89.45] < 0.001 p_Lymph_WBC, Median [Q1-Q3] 20.85 [14.50;28.75] 11.70 [6.82;23.10] < 0.001 p_Mono_WBC, Median [Q1-Q3] 5.70 [4.20;6.90] 5.60 [2.75;7.45] 0.98 p_Eos_WBC, Median [Q1-Q3] 1.70 [0.80;3.20] 1.50 [0.23;2.80] 0.121 p_Baso_WBC, Median [Q1-Q3] 0.40 [0.30;0.60] 0.40 [0.20;0.50] 0.299 p_Neut, Median [Q1-Q3] 5.47 [4.07;7.35] 7.74 [4.43;10.95] 0.002 p_Lymph, Median [Q1-Q3] 1.56 [1.13;2.10] 1.09 [0.72;1.47] < 0.001 p_Mono, Median [Q1-Q3] 0.42 [0.28;0.57] 0.48 [0.26;0.74] 0.145 p_Eos, Median [Q1-Q3] 0.13 [0.06;0.24] 0.14 [0.02;0.23] 0.237 p_Baso, Median [Q1-Q3] 0.03 [0.02;0.05] 0.04 [0.02;0.05] 0.449 p_RBC, Median [Q1-Q3] 4.20 [3.81;4.65] 3.76 [3.38;4.35] < 0.001 p_HGB, Mean (SD) 119.45 (18.54) 104.81 (20.99) < 0.001 p_HCT, Median [Q1-Q3] 0.36 [0.33;0.40] 0.31 [0.27;0.37] < 0.001 p_MCV, Median [Q1-Q3] 87.50 [83.60;90.77] 86.65 [80.32;88.55] 0.076 p_MCH, Median [Q1-Q3] 29.10 [27.30;30.30] 29.00 [26.25;29.78] 0.142 p_MCHC, Mean (SD) 329.34 (14.99) 328.39 (13.89) 0.638 p_RDW, Median [Q1-Q3] 12.80 [12.20;13.70] 13.20 [12.53;14.60] 0.017 p_PLT, Median [Q1-Q3] 241.50 [201.00;300.75] 259.50 [193.25;309.25] 0.705 p_MPV, Median [Q1-Q3] 9.70 [9.30;10.30] 9.90 [9.30;10.30] 0.503 p_PCT, Median [Q1-Q3] 0.24 [0.20;0.29] 0.25 [0.21;0.31] 0.7 p_BUA, Median [Q1-Q3] 267.50 [202.48;341.40] 255.50 [188.20;315.20] 0.238 p_BUN, Median [Q1-Q3] 4.60 [3.50;6.03] 4.75 [3.69;6.30] 0.753 p_Scr, Median [Q1-Q3] 100.00 [78.00;132.00] 107.00 [80.00;141.50] 0.25 p_eGFR, Median [Q1-Q3] 67.09 [48.27;89.05] 65.48 [32.54;81.62] 0.189 p_HCO3, Median [Q1-Q3] 22.70 [20.80;24.50] 21.30 [19.92;23.58] 0.014 p_beta2_MG, Median [Q1-Q3] 2.42 [1.92;3.38] 2.83 [2.20;5.01] 0.008 p_TP, Mean (SD) 65.80 (5.85) 63.41 (7.47) 0.036 p_ALB, Median [Q1-Q3] 36.00 [33.45;38.55] 33.20 [30.18;36.20] < 0.001 p_GLB, Median [Q1-Q3] 29.50 [26.80;32.45] 29.85 [25.58;33.50] 0.901 p_ALBGLB, Median [Q1-Q3] 1.20 [1.10;1.40] 1.10 [0.90;1.33] 0.02 p_BIL, Median [Q1-Q3] 9.00 [6.55;12.00] 9.75 [7.15;14.80] 0.142 p_DBIL, Median [Q1-Q3] 4.20 [3.20;5.50] 5.00 [4.00;6.90] 0.003 p_I_Bil, Median [Q1-Q3] 4.80 [3.20;6.70] 4.75 [3.03;6.00] 0.551 p_GPT, Median [Q1-Q3] 12.50 [9.00;18.00] 13.50 [8.85;21.52] 0.403 p_GOT, Median [Q1-Q3] 15.00 [12.00;18.00] 17.50 [13.00;24.08] 0.016 p_ALP, Median [Q1-Q3] 63.00 [52.50;75.00] 62.00 [49.50;78.50] 0.855 p_GGT, Median [Q1-Q3] 24.80 [17.00;36.00] 35.00 [16.75;79.50] 0.017 p_TBA, Median [Q1-Q3] 1.90 [1.10;3.50] 2.60 [1.40;5.15] 0.013 p_K, Median [Q1-Q3] 3.89 [3.59;4.15] 3.66 [3.39;3.88] < 0.001 p_Ca, Median [Q1-Q3] 2.19 [2.12;2.27] 2.12 [2.04;2.23] 0.002 p_PT, Median [Q1-Q3] 11.70 [11.28;12.40] 12.40 [11.50;12.90] 0.092 p_INR, Median [Q1-Q3] 1.02 [0.98;1.08] 1.08 [1.00;1.13] 0.087 p_PTA, Mean (SD) 102.64 (17.46) 91.67 (17.64) 0.035 p_TT, Median [Q1-Q3] 18.25 [17.40;19.22] 18.10 [17.25;19.80] 0.838 p_APTT, Median [Q1-Q3] 26.30 [23.78;29.05] 25.40 [22.00;28.50] 0.601 p_PF, Median [Q1-Q3] 3.42 [2.87;4.14] 3.24 [2.98;4.77] 0.785 p_NLR, Median [Q1-Q3] 3.36 [2.16;5.35] 6.88 [2.82;12.89] < 0.001 p_PLR, Median [Q1-Q3] 152.21 [109.85;230.10] 230.65 [157.83;360.10] < 0.001 p_LMR, Median [Q1-Q3] 4.16 [2.84;5.92] 2.67 [1.51;3.95] < 0.001 p_ELR, Median [Q1-Q3] 0.08 [0.04;0.14] 0.08 [0.04;0.18] 0.427 p_dNLR, Median [Q1-Q3] 2.28 [1.60;3.65] 3.90 [1.98;8.45] < 0.001 p_NLPR, Median [Q1-Q3] 0.01 [0.01;0.02] 0.02 [0.01;0.06] 0.001 p_SII, Median [Q1-Q3] 813.30 [503.18;1427.04] 1864.08 [791.33;3020.20] < 0.001 p_AISI, Median [Q1-Q3] 329.31 [189.52;556.50] 689.22 [266.96;1807.54] < 0.001 p_LCR, Median [Q1-Q3] 0.55 [0.16;1.75] 0.04 [0.01;0.70] < 0.001 p_SIRI, Median [Q1-Q3] 1.31 [0.77;2.24] 2.47 [1.11;5.76] < 0.001 p_CRPp_ALB, Median [Q1-Q3] 0.08 [0.02;0.24] 0.84 [0.07;1.91] < 0.001 p_PCTp_ALB, Median [Q1-Q3] < 0.01 [< 0.01;<0.01] 0.02 [< 0.01;0.39] < 0.001 WBCp_WBC, Median [Q1-Q3] 0.92 [0.72;1.11] 0.81 [0.58;1.00] 0.014 p_T, Median [Q1-Q3] 36.80 [36.70;36.90] 38.55 [36.82;39.18] < 0.001 p_SBP, Median [Q1-Q3] 131.00 [121.00;146.00] 126.00 [114.50;143.50] 0.09 p_DBP, Median [Q1-Q3] 78.00 [72.00;86.00] 78.00 [68.00;87.50] 0.682 p_HR, Median [Q1-Q3] 76.00 [68.00;83.00] 92.50 [84.25;102.00] < 0.001 p_RR, Median [Q1-Q3] 20.00 [18.00;20.00] 20.00 [19.25;20.00] < 0.001 Barthel_Index, Median [Q1-Q3] 40.00 [30.00;85.00] 65.00 [30.00;88.75] 0.206 VTE, Median [Q1-Q3] 2.00 [1.00;3.00] 2.00 [1.50;3.00] 0.515 Surgery, N (%): 0.001 PCNL 172 (35.98%) 30 (55.56%) RIRS 128 (26.78%) 17 (31.48%) Others 178 (37.24%) 7 (12.96%) Sex, N (%): 0.202 male 217 (45.40%) 30 (55.56%) female 261 (54.60%) 24 (44.44%) RR, Median [Q1-Q3] 20.00 [20.00;20.00] 20.00 [20.00;20.00] 0.907 U_culture, N (%): 0.857 0 423 (88.49%) 47 (87.04%) 1 9 (1.88%) 1 (1.85%) TRUE 46 (9.62%) 6 (11.11%) U_LEU, Median [Q1-Q3] 1.00 [0.00;4.00] 3.50 [1.00;4.00] 0.003 U_NIT, N (%): 0.116 0 448 (93.72%) 50 (92.59%) 1 15 (3.14%) 0 (0.00%) 2 15 (3.14%) 4 (7.41%) U_PRO, Median [Q1-Q3] 0.00 [0.00;1.00] 0.00 [0.00;1.00] 0.535 U_GLU, Median [Q1-Q3] 0.00 [0.00;2.00] 0.00 [0.00;0.00] 0.088 U_URO, N (%): 1 0 472 (98.74%) 54 (100.00%) 1 2 (0.42%) 0 (0.00%) 2 3 (0.63%) 0 (0.00%) 3 1 (0.21%) 0 (0.00%) U_BIL, N (%): 1 0 473 (98.95%) 54 (100.00%) 2 2 (0.42%) 0 (0.00%) 3 3 (0.63%) 0 (0.00%) OB, Median [Q1-Q3] 2.00 [0.00;3.00] 1.00 [0.00;2.00] 0.046 p_CNS, N (%): 0.697 1 432 (90.38%) 48 (88.89%) 2 2 (0.42%) 0 (0.00%) 4 44 (9.21%) 6 (11.11%) ASA, N (%): 0.85 1 20 (4.18%) 3 (5.56%) 2 439 (91.84%) 49 (90.74%) 3 19 (3.97%) 2 (3.70%) Morse, Median [Q1-Q3] 4.00 [4.00;5.00] 4.00 [4.00;5.00] 0.628 BMI, Body Mass Index; T, Temperature;HR, Heart Rate; SBP, Systolic Blood Pressure; DBP, Diastolic Blood Pressure; SG, Specific Gravity; SED_RBC, Sediment Red Blood Cells, SED_WBC, Sediment White Blood Cells; SED_EC, Sediment Epithelial Cells; SED_casts, Sediment Casts; SED_bacteria, Sediment Bacteria; U_conductivity, Urine Conductivity; WBC, White Blood Cell Count; Neut_WBC, Neutrophil WBC; Lymph_WBC, Lymphocyte WBC; Mono_WBC, Monocyte WBC; Eos_WBC, Eosinophil WBC; Baso_WBC, Basophil WBC; Neut, Neutrophil Percentage; Lymph, Lymphocyte Percentage; Mono, Monocyte Percentage; Eos, Eosinophil Percentage; Baso, Basophil Percentage; RBC, Red Blood Cell Count; HGB, Hemoglobin; HCT, Hematocrit; MCV, Mean Corpuscular Volume; MCH, Mean Corpuscular Hemoglobin; MCHC, Mean Corpuscular Hemoglobin Concentration; RDW, Red Cell Distribution Width; PLT, Platelet Count; MPV, Mean Platelet Volume; B_PCT, Blood Platelet Count; BUA, Blood Uric Acid; BUN, Blood Urea Nitrogen; Scr, Serum Creatinine; eGFR, Estimated Glomerular Filtration Rate; HCO3, Bicarbonate; beta2_MG, Beta-2 Microglobulin; CysC, Cystatin C; TP, Total Protein; ALB, Albumin; GLB, Globulin; ALB_GLB, Albumin to Globulin Ratio; BIL, Total Bilirubin; DBIL, Direct Bilirubin; I_Bil, Indirect Bilirubin; GPT, Glutamic Pyruvic Transaminase; GOT, Glutamic Oxaloacetic Transaminase; ALP, Alkaline Phosphatase; GGT, Gamma-Glutamyl Transferase; TBA, Total Bile Acids; CRP, C-Reactive Protein; K, Potassium; Ca, Calcium; PT, Prothrombin Time; INR, International Normalized Ratio; PTA, Prothrombin Time Activity; TT, Thrombin Time; APTT, Activated Partial Thromboplastin Time; PF, Platelet Factor; NLR, Neutrophil to Lymphocyte Ratio; PLR, Platelet to Lymphocyte Ratio; LMR, Lymphocyte to Monocyte Ratio; ELR, Eosinophil to Lymphocyte Ratio; dNLR, Derived Neutrophil to Lymphocyte Ratio; NLPR, Neutrophil to Lymphocyte and Platelet Ratio; SII, Systemic Inflammatory Index; AISI, Adjusted Inflammatory Score Index; SIRI, Systemic Immune-Inflammatory Index; LCR, Lymphocyte to Creatinine Ratio; CRP_ALB, C-Reactive Protein to Albumin Ratio; p_CRP, Procalcitonin; p_SAA, Serum Amyloid A; p, postoperative. After considering both Lasso regression and Boruta algorithm-selected features, four key predictors were initially selected: p_IL_6, p_PCT/p_ALB, p_T, and p_HR. These four predictor variables were then subjected to Pearson correlation analysis (Fig. 2 D). The results showed that there was no strong correlation between the feature variables (r < 0.7), indicating that the features were relatively independent and did not redundantly express the same information. This is beneficial for improving the model's generalization ability, robustness, and interpretability. Therefore, these four feature variables were ultimately included (Fig. 2 E). Comparison of the Performance of 9 Machine Learning Algorithms All patients were randomly divided into a training cohort (70%) and a validation cohort (30%). To reduce the instability and overfitting of the prediction results, 10-fold cross-validation was used to determine the model’s average prediction accuracy. Model performance was comprehensively evaluated using AUC, accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), F1 score, and Kappa value[12]. The results showed that the nine machine learning models demonstrated good discrimination ability in both the training and validation cohorts(Table 2 ). Among them, the XGBoost, LightGBM, RandomForest, AdaBoost, and GBDT models had an AUC value of 1.00 in the training cohort, while their AUC values in the validation cohort were 0.86, 0.84, 0.83, 0.77, and 0.83, respectively, suggesting potential overfitting. On the other hand, the logistic regression, GNB, KNN, and SVM models exhibited more consistent AUC and accuracy between the training and validation cohorts, indicating no significant overfitting. Among these, logistic regression showed the best performance in predicting the risk of postoperative infectious urosepsis in diabetic patients with urinary stones, particularly in terms of AUC, demonstrating a significant advantage (Figs. 3 a-b). Therefore, we concluded that the logistic regression model outperformed other machine learning models in predicting the risk of postoperative infectious urosepsis and selected it as our final predictive model. Table 2 Performance of Each Model in the Training and Validation Cohort. Cohort Models AUC(95%CI) cutoff(95%CI) ACC(95%CI) TPR(95%CI) TNR(95%CI) PPV(95%CI) NPV(95%CI) F1 Score(95%CI) Kappa(95%CI) Training logistic 0.91 (0.84–0.97) 0.16(0.14–0.17) 0.91(0.90–0.92) 0.79(0.77–0.81) 0.92(0.91–0.94) 0.59(0.55–0.62) 0.97(0.97–0.97) 0.67(0.65–0.69) 0.62(0.59–0.65) XGBoost 1.00 (NaN-NaN) 0.67(0.64–0.71) 1.0(1.00–1.00) 1.0(1.00–1.00) 1.0(1.00–1.00) 1.0(1.00–1.00) 1.0(1.00–1.00) 1.0(1.00–1.00) 1.0(1.00–1.00) LightGBM 1.00 (NaN-NaN) 0.9(0.88–0.91) 1.0(1.00–1.00) 1.0(1.00–1.00) 1.0(1.00–1.00) 1.0(1.00–1.00) 1.0(1.00–1.00) 1.0(1.00–1.00) 1.0(1.00–1.00) RandomForest 1.00 (NaN-NaN) 0.53(0.50–0.56) 1.0(1.00–1.00) 1.0(1.00–1.00) 1.0(1.00–1.00) 1.0(1.00–1.00) 1.0(1.00–1.00) 1.0(1.00–1.00) 1.0(1.00–1.00) AdaBoost 1.00 (NaN-NaN) 0.5(0.50–0.50) 1.0(0.99-1.00) 1.0(1.00–1.00) 1.0(0.99-1.00) 0.98(0.95-1.00) 1.0(1.00–1.00) 0.99(0.97-1.00) 0.99(0.97-1.00) GBDT 1.00 (NaN-NaN) 0.82(0.79–0.84) 1.0(1.00–1.00) 1.0(1.00–1.00) 1.0(1.00–1.00) 1.0(1.00–1.00) 1.0(1.00–1.00) 1.0(1.00–1.00) 1.0(1.00–1.00) GNB 0.90 (0.83–0.96) 0.0(0.00–0.00) 0.87(0.86–0.88) 0.83(0.81–0.85) 0.87(0.86–0.89) 0.47(0.45–0.49) 0.98(0.97–0.98) 0.6(0.58–0.62) 0.53(0.51–0.55) KNN 0.97 (0.95–0.99) 0.2(0.20–0.20) 0.85(0.84–0.86) 1.0(1.00–1.00) 0.83(0.82–0.84) 0.44(0.42–0.46) 1.0(1.00–1.00) 0.62(0.60–0.63) 0.54(0.52–0.56) SVM 0.87 (0.77–0.96) 0.1(0.08–0.12) 0.93(0.93–0.94) 0.75(0.73–0.77) 0.96(0.95–0.97) 0.72(0.67–0.76) 0.97(0.96–0.97) 0.73(0.71–0.75) 0.69(0.67–0.72) Validation logistic 0.90 (NaN-NaN) 0.16(0.14–0.17) 0.89(0.85–0.92) 0.74(0.58–0.90) 0.91(0.87–0.94) 0.54(0.44–0.63) 0.96(0.94–0.99) 0.6(0.49–0.72) 0.54(0.41–0.67) XGBoost 0.86 (NaN-NaN) 0.67(0.64–0.71) 0.94(0.93–0.95) 0.61(0.47–0.74) 0.98(0.97-1.00) 0.88(0.79–0.98) 0.95(0.94–0.97) 0.68(0.60–0.77) 0.65(0.56–0.74) LightGBM 0.84 (NaN-NaN) 0.9(0.88–0.91) 0.93(0.90–0.95) 0.42(0.25–0.60) 1.0(0.99-1.00) nan(NaN-NaN) 0.93(0.91–0.95) nan(NaN-NaN) 0.51(0.31–0.72) RandomForest 0.83 (NaN-NaN) 0.53(0.50–0.56) 0.94(0.91–0.96) 0.62(0.44–0.81) 0.98(0.96-1.00) 0.89(0.78–1.01) 0.95(0.93–0.98) 0.68(0.54–0.82) 0.65(0.51–0.80) AdaBoost 0.77 (NaN-NaN) 0.5(0.50–0.50) 0.92(0.88–0.96) 0.52(0.28–0.76) 0.97(0.95-1.00) nan(NaN-NaN) 0.94(0.91–0.97) nan(NaN-NaN) 0.52(0.27–0.78) GBDT 0.83 (NaN-NaN) 0.82(0.79–0.84) 0.93(0.91–0.96) 0.48(0.29–0.68) 0.99(0.98-1.00) nan(NaN-NaN) 0.94(0.91–0.96) nan(NaN-NaN) 0.55(0.33–0.76) GNB 0.89 (NaN-NaN) 0.0(0.00–0.00) 0.86(0.82–0.90) 0.78(0.64–0.91) 0.87(0.84–0.91) 0.46(0.36–0.56) 0.97(0.95–0.99) 0.57(0.46–0.68) 0.49(0.37–0.62) KNN 0.82 (NaN-NaN) 0.2(0.20–0.20) 0.8(0.77–0.84) 0.71(0.56–0.86) 0.82(0.78–0.85) 0.34(0.28–0.41) 0.96(0.93–0.98) 0.45(0.37–0.54) 0.35(0.26–0.45) SVM 0.85 (NaN-NaN) 0.1(0.08–0.12) 0.91(0.88–0.93) 0.71(0.56–0.86) 0.93(0.90–0.96) 0.62(0.51–0.74) 0.96(0.94–0.98) 0.63(0.53–0.73) 0.58(0.47–0.69) ROC, receiver operating characteristic curve; Logistic, Logistic Regression; XGBoost, Extreme Gradient Boosting; LightGBM, Light Gradient Boosting Machine; AdaBoost, Adaptive Boosting;GBDT, Gradient Boosting Decision Tree; GNB, Gaussian Naive Bayes; KNN, K-Nearest Neighbor;SVM, Support Vector Machine. Best Model Performance Given that the logistic regression model performed excellently in the initial modeling stage, we further validated its generalizability and robustness by randomly dividing the 532 patients into training, validation, and testing sets in a 4:4:2 ratio. Subsequently, 10-fold cross-validation was conducted on the training and validation cohorts, yielding average AUC values of 0.92 and 0.90, respectively. Based on these results, we further evaluated the model on an independent testing cohort, achieving an AUC of 0.87 (Figs. 4 a-c). These results indicate that the model maintained good predictive performance across different datasets, demonstrating strong generalizability and robustness. To assess the model's performance and verify its clinical significance, we evaluated the model using learning curves, calibration curves, and decision curve analysis[13–15]. The learning curve results showed that the model fit well and remained stable between the training and validation cohorts (Fig. 5 a), avoiding both underfitting and overfitting. The calibration curve further confirmed that the predicted probabilities from the logistic regression model closely matched the actual probabilities (Fig. 5 b), indicating that the model has high accuracy in probabilistic prediction. Furthermore, decision curve analysis demonstrated that the postoperative infectious urosepsis risk assessment model provided significant clinical net benefit within a threshold range of 5% to 90%, further validating its reliability and potential clinical application as a predictive tool (Fig. 5 c). Model Interpretability A major limitation of machine learning is its difficulty in providing direct interpretability, which is often unacceptable in clinical practice[16]. To address this issue and assess the contribution of each feature to the prediction, we used SHAP analysis to interpret the logistic regression model[17]. The results showed that, among the four feature variables, p_T exhibited the highest SHAP value distribution and was the most influential predictor (Figs. 6 a-b). To further elucidate the decision-making process in individual cases, additional analysis revealed that in high-risk cases, elevated values of p_T and p_HR were the main drivers of increased risk (Fig. 6 c). In contrast, in low-risk cases, lower levels of these variables led to reduced risk estimates (Fig. 6 d). Overall, SHAP analysis provided both global and local interpretability, confirming that the model relies on clinically reasonable features, thereby enhancing its credibility and practical application potential in perioperative infection risk assessment. Discussion The risk of postoperative sepsis is significantly increased in diabetic patients with urinary stones. Hyperglycemic conditions impair immune function, increasing susceptibility to infections[18]. Additionally, factors such as the complexity of the stones and surgical trauma further elevate the risk of postoperative urosepsis[19]. In this study, we constructed an interpretable risk prediction model for postoperative infectious urosepsis by incorporating four core predictive factors—p_IL_6, p_PCT/p_ALB, p_T, and p_HR—using multimodal clinical data and applying LASSO regression and Boruta algorithms. The results showed that the logistic regression model outperformed the other nine machine learning methods, with excellent performance in terms of prediction accuracy, sensitivity, and specificity. This model provides a valuable tool for early identification of high-risk patients and helps develop more personalized management strategies, ultimately improving clinical decision-making. Previous studies have reported that factors influencing the risk of postoperative urosepsis include specific stone components, diabetes, surgical complexity, and metabolic abnormalities in patients[20]. Notably, diabetes itself can be an independent predictor of postoperative sepsis[21]. Therefore, timely assessment of the risk of infectious urosepsis following surgery for stones in diabetic patients, and the implementation of preventive measures, can help reduce the incidence of postoperative infections and optimize resource allocation, thereby decreasing unnecessary treatments and hospitalization costs and improving healthcare efficiency. Before the widespread application of artificial intelligence, nomograms were commonly used as clinical disease prediction models[22–24]. Yang et al. developed a nomogram that integrates renal pelvic pressure to predict the probability of urosepsis after percutaneous nephrolithotomy (PCNL), incorporating clinical features such as single kidney[25], nitrite-positive urine, surgery duration ≥ 75 minutes, recurrent urinary tract infections, and diabetes history. The AUC value in the training cohort was 0.887, and in the validation cohort, it was 0.864. However, nomograms have certain limitations, such as model overfitting, which can reduce prediction accuracy, and their susceptibility to confounding factors. Consequently, these traditional models are gradually being replaced by machine learning-based models. To our knowledge, we have conducted a comprehensive review of multimodal clinical data, including demographics, vital signs, inflammation and infection indicators, surgical information, and routine laboratory tests, covering 164 clinical multimodal features. The interpretable risk prediction model for postoperative infectious urosepsis we constructed is the most comprehensive study on postoperative urosepsis prediction to date. The AUC values of this model were 0.916 in the training cohort, 0.903 in the validation cohort, and 0.866 in the test cohort, with model performance validated through learning curves, calibration curves, and decision curves. Using the SHAP values of the machine learning model, we were able to explain and visualize the prediction results. The most important variables were p_T, p_HR, p_IL_6, and p_PCT/p_ALB. Previous studies have confirmed that p_T, p_HR, p_IL_6, and p_PCT/p_ALB are risk factors for postoperative infectious urosepsis. Research has shown that specific thresholds of postoperative heart rate are significantly associated with the risk of sepsis[26–27]. For example, patients with a P wave less than 103 milliseconds or a PR interval less than 157 milliseconds have an increased risk of postoperative sepsis by 2.06 or 2.33 times, respectively. Increased temperature combined with CRP or PCT levels has a specificity of 87.5% for predicting urosepsis[28]. Postoperative IL-6 and p_PCT/p_ALB have been identified as early biomarkers for urosepsis[29]. IL-6 reflects the intensity of the inflammatory response, while p_PCT/p_ALB integrates information on infection and metabolic status, reflecting the balance between inflammation and nutritional status. Both, in combination with other indicators, can optimize prediction models[30–31], especially in diabetic patients with upper urinary tract stones, as their immune systems may be more vulnerable. An increase in this ratio helps in the early detection of the risk of infectious urosepsis. However, despite the potential clinical application value, several limitations should be considered. First, this study was conducted in a single clinical research center in China with a relatively small sample size, and there may be regional biases. This could limit the generalizability of the model. Second, as this is a retrospective study, prospective cohort studies in more external hospital datasets are needed to validate the model’s external validity. Additionally, more rigorous cross-validation strategies should be employed to optimize its generalizability. In conclusion, this study developed an interpretable machine learning model using multimodal clinical data for the risk assessment of postoperative infectious urosepsis in diabetic patients with urinary stones. The results show that this model has high accuracy and interpretability, effectively helping clinicians identify high-risk patients and providing a basis for personalized treatment. However, the study has certain limitations, and future research should further validate the model's generalizability through prospective multicenter studies. Abbreviations We extend our deepest appreciation to all study participants whose trust and dedication made this research possible. Declarations Authors’ contributions Conception and design: Fubo Wang. Data acquisition: Dongwei Pan, Zuheng Wang Data analysis and interpretation: Dianyu Wang, Zequn Su Drafting the manuscript: Dongwei Pan, Zuheng Wang Critical revision of the manuscript for scientific and factual content: Fubo Wang, Junyi Chen Statistical analysis:Chunmeng Wei, Junhao Mi, Mingda Wang Supervision: Fubo Wang Funding This research received financial support from two funding sources: first, a grant (No. 82372828, principal investigator: F.W.) from the National Natural Science Foundation of China (NSFC); second, a grant (No. 2023GXNSFFA026003, principal investigator: F.W.) for the Science Foundation for Distinguished Young Scholars of Guangxi, affiliated with Guangxi Medical University. Data availability Any inquiries regarding the data and materials should be directed to the corresponding authors. Ethics Approval and Consent to Participate Approval statement The study was approved by the Ethics Committee of Guangxi Medical University. Clinical trial number: ChiCTR2400079409 on January 3, 2024 . Accordance statement This study strictly adhered to the ethical principles outlined in the Declaration of Helsinki, ensuring that all data were derived from actual clinical cases. Informed Consent statement Informed consent was obtained from each patient or their legal representative before sample collection. Consent for Publication Not applicable. Competing Interests The authors declare that they have no competing interests. References Gao C, Liu J, Wang D, Liu M, Qiu J. Risk factors and an optimized prediction model for urosepsis in diabetic patients with upper urinary tract stones. Sci Rep . 2025;15(1):8183. Wei J, Zeng R, Liang R, et al. Construction and validation of a nomogram prediction model for the progression to septic shock in elderly patients with urosepsis. Heliyon . 2024;10(11):e32454. Sun H, Chen Z. Integration of minimally invasive techniques and interventional therapy: application of percutaneous nephrolithotomy in patients with upper urinary tract stones and an analysis of risk factors for postoperative bleeding. Front Med (Lausanne) . 2025;12:1556224. Ying Z, Ming S, Yang R, et al. Comparison of safety and efficacy of negative pressure aspiration assisted retrograde intrarenal surgery and traditional percutaneous nephrolithotomy in the treatment of upper urinary tract stones larger than 2 cm: a systematic review and meta-analysis. Int J Surg . 2025;111(5):3613-3628. Yu W, Yu F, Wang Y, Tang T, Huang X, Wang L. Efficacy and Postoperative Infection following Super Mini Percutaneous Nephrolithotomy vs Flexible Ureteroscopy for Diabetic Nephrolithiasis: A Comparative Analysis and Risk Factors for Postoperative Infectious Complications. J Endourol . 2024;38(10):1082-1091. Alhamad FS, Alathel A, Aljaafri ZA, et al. Predictors of Urosepsis Post Percutaneous Nephrolithotomy at King Abdulaziz Medical City, Riyadh. Cureus . 2023;15(5):e39542. Berman R, Lee J, Balasubramanian A, Shah O. The Association of Perioperative Glycated Hemoglobin (Hemoglobin A1C) and the Risk of Sepsis after Ureteroscopy with Laser Lithotripsy. J Endourol . 2025;39(6):549-555. Liu Y, Sun Q, Long H, et al. The value of IL-6, PCT, qSOFA, NEWS, and SIRS to predict septic shock after Percutaneous nephrolithotomy. BMC Urol . 2024;24(1):116. Zeng QB, Peng EL, Zhou Y, et al. Explainable machine learning model for predicting septic shock in critically sepsis patients based on coagulation indexes: A multicenter cohort study. Chin J Traumatol . S1008-1275(25)00032-X Oh MY, Kim HS, Jung YM, Lee HC, Lee SB, Lee SM. Machine Learning-Based Explainable Automated Nonlinear Computation Scoring System for Health Score and an Application for Prediction of Perioperative Stroke: Retrospective Study. J Med Internet Res . 2025;27:e58021. Remeseiro B, Bolon-Canedo V. A review of feature selection methods in medical applications. Comput Biol Med . 2019;112:103375. Butala NM, Strom JB, Faridi KF, et al. Validation of Administrative Claims to Ascertain Outcomes in Pivotal Trials of Transcatheter Aortic Valve Replacement. JACC Cardiovasc Interv . 2020;13(15):1777-1785. Huang Y, Li W, Macheret F, Gabriel RA, Ohno-Machado L. A tutorial on calibration measurements and calibration models for clinical prediction models. J Am Med Inform Assoc . 2020;27(4):621-633. Netto Flores Cruz G, Korthauer K. Bayesian Decision Curve Analysis With Bayesdca. Stat Med . 43,30 (2024): 6042-6058. Vickers AJ, Van Calster B, Steyerberg EW. Net benefit approaches to the evaluation of prediction models, molecular markers, and diagnostic tests. BMJ . 2016;352:i6. da Cruz HF, Pfahringer B, Martensen T, et al. Using interpretability approaches to update "black-box" clinical prediction models: an external validation study in nephrology. Artif Intell Med . 2021;111:101982. Hu J, Xu J, Li M, et al. Identification and validation of an explainable prediction model of acute kidney injury with prognostic implications in critically ill children: a prospective multicenter cohort study. EClinicalMedicine . 2024;68:102409. Berman R, Lee J, Balasubramanian A, Shah O. The Association of Perioperative Glycated Hemoglobin (Hemoglobin A1C) and the Risk of Sepsis after Ureteroscopy with Laser Lithotripsy. J Endourol . 2025;39(6):549-555. Wang L, Yu X, Qiu Z, et al. Influence of preoperative urine culture and bacterial species on urogenital sepsis after ureteral flexible lithotripsy in patients with upper urinary tract stones. Front Med (Lausanne) . 2024;11:1393734. Li Z, Fu C, Sun C, Suo Y, Li K, Qi S. Analysis of metabolic syndrome in bilateral upper urinary tract stones: A retrospective study of 3905 cases. Heliyon . 2024;10(10):e31180. Cao Y, Cao H. Pathogen distribution and risk factors of positive stone culture for patients with upper urinary tract stone. Am J Transl Res . 2025;17(5):3658-3664. Wang R, Dai W, Gong J, et al. Development of a novel combined nomogram model integrating deep learning-pathomics, radiomics and immunoscore to predict postoperative outcome of colorectal cancer lung metastasis patients. J Hematol Oncol . 2022;15(1):11. Huang Y, Wang X, Cao Y, et al. Nomogram for Predicting Neoadjuvant Chemotherapy Response in Breast Cancer Using MRI-based Intratumoral Heterogeneity Quantification. Radiology . 315,1 (2025): e241805. Gandaglia G, Ploussard G, Valerio M, et al. A Novel Nomogram to Identify Candidates for Extended Pelvic Lymph Node Dissection Among Patients with Clinically Localized Prostate Cancer Diagnosed with Magnetic Resonance Imaging-targeted and Systematic Biopsies. Eur Urol . 2019;75(3):506-514. Yang M, Li Y, Huang F. A nomogram for predicting postoperative urosepsis following retrograde intrarenal surgery in upper urinary calculi patients with negative preoperative urine culture. Sci Rep . 2023;13(1):2123. Xie W, Wu L, Yang M, Luo H, Li W, Li H. Association of preoperative electrocardiographic markers with sepsis in elderly patients after general surgery. BMC Cardiovasc Disord . 2023;23(1):485. Shrestha N, Zorn-Pauly K, Mesirca P, et al. Lipopolysaccharide-induced sepsis impairs M2R-GIRK signaling in the mouse sinoatrial node. Proc Natl Acad Sci U S A . 2023;120(28):e2210152120. Jiaping W, Tingting H, Ming H, et al. Application of peripheral blood monocyte distribution width in the diagnosis of urosepsis. Diagn Microbiol Infect Dis . 2025;113(1):116889. Liu S, Wang X, She F, Zhang W, Liu H, Zhao X. Effects of Neutrophil-to-Lymphocyte Ratio Combined With Interleukin-6 in Predicting 28-Day Mortality in Patients With Sepsis. Front Immunol . 2021;12:639735. Wu Y, Wang G, Huang Z, et al. Diagnostic and therapeutic value of biomarkers in urosepsis. Ther Adv Urol . 2023;15:17562872231151852. Peng X, Jing X, Li T, Cheng J. Serum of interleukin-6 and procalcitonin as early diagnostic markers for the identification of poor hematopoietic reconstitution following allogeneic hematopoietic stem cell transplantation. Cancer . 2025;131(7):e35835. Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 02 Apr, 2026 Reviews received at journal 01 Apr, 2026 Reviewers agreed at journal 31 Mar, 2026 Reviews received at journal 19 Nov, 2025 Reviewers agreed at journal 11 Nov, 2025 Reviewers invited by journal 10 Oct, 2025 Editor assigned by journal 17 Sep, 2025 Submission checks completed at journal 17 Sep, 2025 First submitted to journal 10 Sep, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7584146","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":533374441,"identity":"0f1817ed-da78-4527-bf27-8d09a41c76c4","order_by":0,"name":"Dianyu Wang","email":"","orcid":"","institution":"Guangxi Medical University","correspondingAuthor":false,"prefix":"","firstName":"Dianyu","middleName":"","lastName":"Wang","suffix":""},{"id":533374442,"identity":"f7990cd4-3f3a-41f0-aac8-9628113bfe0a","order_by":1,"name":"Dongwei Pan","email":"","orcid":"","institution":"The Second Affiliated Hospital of Fujian Medical University","correspondingAuthor":false,"prefix":"","firstName":"Dongwei","middleName":"","lastName":"Pan","suffix":""},{"id":533374443,"identity":"3c827cea-80da-48f9-afec-e511dabb6b5a","order_by":2,"name":"Zuheng Wang","email":"","orcid":"","institution":"Guangxi Medical University","correspondingAuthor":false,"prefix":"","firstName":"Zuheng","middleName":"","lastName":"Wang","suffix":""},{"id":533374444,"identity":"9152a36e-0036-4bb6-b031-7cce73de4e30","order_by":3,"name":"Zequn Su","email":"","orcid":"","institution":"Guangxi Medical University","correspondingAuthor":false,"prefix":"","firstName":"Zequn","middleName":"","lastName":"Su","suffix":""},{"id":533374445,"identity":"22a0a22f-2a50-40f0-92f4-e1ddcb8f24f7","order_by":4,"name":"Junhao Mi","email":"","orcid":"","institution":"Liuzhou Maternity and Child Healthcare Hospital","correspondingAuthor":false,"prefix":"","firstName":"Junhao","middleName":"","lastName":"Mi","suffix":""},{"id":533374446,"identity":"bee3fa0a-2a52-49b2-9f50-ff25dc3b4bda","order_by":5,"name":"Mingda Wang","email":"","orcid":"","institution":"The Second Affiliated Hospital of Fujian Medical University","correspondingAuthor":false,"prefix":"","firstName":"Mingda","middleName":"","lastName":"Wang","suffix":""},{"id":533374447,"identity":"30b183d6-5e3f-4cfc-b8c3-759b229807f3","order_by":6,"name":"Chunmeng Wei","email":"","orcid":"","institution":"Guangxi Medical University","correspondingAuthor":false,"prefix":"","firstName":"Chunmeng","middleName":"","lastName":"Wei","suffix":""},{"id":533374448,"identity":"e211a081-1229-4056-b1dc-2fb237929a45","order_by":7,"name":"Junyi Chen","email":"","orcid":"","institution":"The Second Affiliated Hospital of Fujian Medical University","correspondingAuthor":false,"prefix":"","firstName":"Junyi","middleName":"","lastName":"Chen","suffix":""},{"id":533374449,"identity":"e5fba020-1f76-4ea7-8a96-ce6388721d6a","order_by":8,"name":"Fubo Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5UlEQVRIie3QMQrCMBSA4YjQqdC1Du0ZAsHoIHoVi9CpOIqjIHTUVcEjOBQE51cCdqm6RnRwCg4d9ASaiHNaN8H8Q5LhfSQEIZPpVxsjQM7nXJtUIrkkjcnXBENVgrM9u6XxxSfHdXNjo46XQF1ctSQfhu00FoRyEZ5tFJIErBbWEQoRJY+YBVvOdpKwIAHbcrXkWFCcSrJZpLEkzwqER+SqSOJM1S1QTnq8oAgOgrjcCk8rPCBLZlEtacwjcofRxXfmOeXFuOvNsqnQEtnnGW5fLuqr6iXzauT+3hwoHzWZTKb/7AW9iVaOt47hEAAAAABJRU5ErkJggg==","orcid":"","institution":"Guangxi Medical University","correspondingAuthor":true,"prefix":"","firstName":"Fubo","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2025-09-10 14:53:41","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7584146/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7584146/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":94361594,"identity":"1c70fc32-c267-4a08-9832-a03fc07454ef","added_by":"auto","created_at":"2025-10-27 13:04:14","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":38729,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.docx","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/9350fd2e2ee47f2c04814670.docx"},{"id":94362616,"identity":"f93b523b-a4f7-4c9a-994d-56f4537637c1","added_by":"auto","created_at":"2025-10-27 13:05:18","extension":"tiff","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":31647842,"visible":true,"origin":"","legend":"","description":"","filename":"figure1.tiff","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/15d0db60a9cc773c3c7ef830.tiff"},{"id":94361759,"identity":"64637702-ee91-4790-a296-0ce305216b51","added_by":"auto","created_at":"2025-10-27 13:04:25","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":41460,"visible":true,"origin":"","legend":"","description":"","filename":"table1.docx","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/7e16f71d273d86e94580281d.docx"},{"id":94362572,"identity":"96be3a31-da0f-413e-ba6e-96dc88f77c52","added_by":"auto","created_at":"2025-10-27 13:05:13","extension":"tif","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16085184,"visible":true,"origin":"","legend":"","description":"","filename":"figure2.tif","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/6e89085f2baf137c8b0ab904.tif"},{"id":94362875,"identity":"94d36a9d-a580-4d6d-9184-94340ce31e1d","added_by":"auto","created_at":"2025-10-27 13:05:32","extension":"docx","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20955,"visible":true,"origin":"","legend":"","description":"","filename":"table2.docx","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/d1656457df7454651ba1a436.docx"},{"id":94362878,"identity":"3e2b78ed-4612-46e6-8854-fe644263c9ce","added_by":"auto","created_at":"2025-10-27 13:05:32","extension":"tif","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":12745684,"visible":true,"origin":"","legend":"","description":"","filename":"figure3.tif","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/6b6f90e7651439804879a5de.tif"},{"id":94362394,"identity":"a0a397a5-c90c-4a8c-9f07-c9570f63e025","added_by":"auto","created_at":"2025-10-27 13:05:07","extension":"tif","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":18433376,"visible":true,"origin":"","legend":"","description":"","filename":"figure4.tif","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/ead7c19ed0f0eb861d2babfa.tif"},{"id":94361634,"identity":"743a54da-007c-49d9-8b03-4f55549fb3fc","added_by":"auto","created_at":"2025-10-27 13:04:16","extension":"tif","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":21391516,"visible":true,"origin":"","legend":"","description":"","filename":"figure5.tif","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/eba9fc92fc1aa4a821d8b4f7.tif"},{"id":94362314,"identity":"09390d16-b5a4-495a-be61-77f67442b21a","added_by":"auto","created_at":"2025-10-27 13:04:59","extension":"tif","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":13844340,"visible":true,"origin":"","legend":"","description":"","filename":"figure6.tif","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/bff967f7e2079dde8ef10d55.tif"},{"id":94362335,"identity":"b334f519-988a-4aca-9df0-b3f79d30bb0c","added_by":"auto","created_at":"2025-10-27 13:05:01","extension":"json","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10428,"visible":true,"origin":"","legend":"","description":"","filename":"cd0e51db20184ff18bd9c99edc9e8455.json","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/1b9101518b3d67acf1424ba1.json"},{"id":94362037,"identity":"f4c3ea31-6419-48e5-ae8f-c73cd81b69eb","added_by":"auto","created_at":"2025-10-27 13:04:44","extension":"xml","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":152120,"visible":true,"origin":"","legend":"","description":"","filename":"cd0e51db20184ff18bd9c99edc9e84551enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/9c645f3c42eafbe876cf1bc1.xml"},{"id":94362284,"identity":"1f7ee8c1-4e6d-4018-89bc-67fab169cb6c","added_by":"auto","created_at":"2025-10-27 13:04:56","extension":"tiff","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":31647842,"visible":true,"origin":"","legend":"","description":"","filename":"figure1.tiff","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/94529e1c80248b9b59e0c8b3.tiff"},{"id":94362391,"identity":"0f85d818-6153-45d3-a144-c1617ef9afd1","added_by":"auto","created_at":"2025-10-27 13:05:07","extension":"tif","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16085184,"visible":true,"origin":"","legend":"","description":"","filename":"figure2.tif","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/5c1f5b3e13f9a58dce5d82cf.tif"},{"id":94362770,"identity":"e4a85be8-e30b-4477-8b03-cf75ac1470bb","added_by":"auto","created_at":"2025-10-27 13:05:25","extension":"tif","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":12745684,"visible":true,"origin":"","legend":"","description":"","filename":"figure3.tif","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/ac24725b52d0ebd7e1d17315.tif"},{"id":94362512,"identity":"34c259c3-04f0-4140-8f2a-6c3c5d10921c","added_by":"auto","created_at":"2025-10-27 13:05:10","extension":"tif","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":18433376,"visible":true,"origin":"","legend":"","description":"","filename":"figure4.tif","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/5db3ad56085561c5d8ddd464.tif"},{"id":94362316,"identity":"b22b10be-23ea-4c4e-99c4-95b765c26571","added_by":"auto","created_at":"2025-10-27 13:04:59","extension":"tif","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":21391516,"visible":true,"origin":"","legend":"","description":"","filename":"figure5.tif","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/ef00140f66169d2365607133.tif"},{"id":94361897,"identity":"90ec2ec9-28d8-4c1b-a8b5-582e47862af2","added_by":"auto","created_at":"2025-10-27 13:04:33","extension":"tif","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":13844340,"visible":true,"origin":"","legend":"","description":"","filename":"figure6.tif","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/5c88fff38d3f54516d2a8711.tif"},{"id":94362761,"identity":"dec6722a-5448-4b78-a733-8d5016578094","added_by":"auto","created_at":"2025-10-27 13:05:25","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":210913,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefigure1.png","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/38b976ed031eb23aa5f0c656.png"},{"id":94362876,"identity":"bf13b0d4-ef6b-4692-8936-f89b6120afdc","added_by":"auto","created_at":"2025-10-27 13:05:32","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":534093,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefigure2.png","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/eee17523c8d49946e22e3b5e.png"},{"id":94362282,"identity":"ae3c1aa4-b45f-4f2e-901e-dd4a1865a9ae","added_by":"auto","created_at":"2025-10-27 13:04:56","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":797570,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefigure3.png","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/f1a011c69529df5315175dc1.png"},{"id":94362615,"identity":"43f444cd-6333-433c-8de6-c01859cab41c","added_by":"auto","created_at":"2025-10-27 13:05:18","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":865995,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefigure4.png","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/6e54dcbd01745dbb5a3795db.png"},{"id":94361976,"identity":"bd5520dc-5940-462b-b5b5-00da50f03a78","added_by":"auto","created_at":"2025-10-27 13:04:41","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":567610,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefigure5.png","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/ed4d553079c8f972a12249dc.png"},{"id":94361738,"identity":"ea3f8d0f-53c9-4b56-b717-09b9d277d72c","added_by":"auto","created_at":"2025-10-27 13:04:22","extension":"png","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":343293,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefigure6.png","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/bd842080d9e6e5549aa8640c.png"},{"id":94362379,"identity":"38566dec-ed16-402c-a4be-44dcd2d75d57","added_by":"auto","created_at":"2025-10-27 13:05:04","extension":"xml","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":149198,"visible":true,"origin":"","legend":"","description":"","filename":"cd0e51db20184ff18bd9c99edc9e84551structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/b01997c261f486ebc3e31324.xml"},{"id":94361939,"identity":"eb5828fe-8ba4-435a-a34f-0ede59872ec8","added_by":"auto","created_at":"2025-10-27 13:04:40","extension":"html","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":155257,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/0fb1a16754d4eeef04b420db.html"},{"id":94361633,"identity":"bd9db645-a41e-4fce-9f10-632456f6442f","added_by":"auto","created_at":"2025-10-27 13:04:16","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":3240344,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eFlowchart of constructing a risk prediction model for postoperative sepsis using multimodal clinical data. \u003c/strong\u003eSHAP, Shapley Additive Explanations.\u003c/p\u003e","description":"","filename":"figure1.png","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/c0800eb7c397ada2e4b16409.png"},{"id":94361761,"identity":"1fce0d39-ed6b-4ffc-92be-d945471aca06","added_by":"auto","created_at":"2025-10-27 13:04:25","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":705499,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eScreening predictive variables of multimodal clinical data using the LASSO regression algorithm and the Boruta algorithm. \u003c/strong\u003eA: Coefficient path plot; B: Ten - fold cross - validation curve; C: Importance ranked by Boruta algorithm; D: Correlation heatmap. E: Venn diagram.LASSO,Least Absolute Shrinkage and Selection Operator.\u003c/p\u003e","description":"","filename":"figure2.png","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/c2755ad757b11a529a3a6310.png"},{"id":94362281,"identity":"d4615f09-d988-45b4-b3fe-82c4ea8f5bf5","added_by":"auto","created_at":"2025-10-27 13:04:55","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":1281995,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eROC curve analysis of each model. \u003c/strong\u003eA: Performance on the training cohort; B: Performance on the validation cohort.ROC, receiver operating characteristic curve; Logistic, Logistic Regression; XGBoost, Extreme Gradient Boosting; LightGBM, Light Gradient Boosting Machine; AdaBoost, Adaptive Boosting;GBDT, Gradient Boosting Decision Tree; GNB, Gaussian Naive Bayes; KNN, K-Nearest Neighbor;SVM, Support Vector Machine.\u003c/p\u003e","description":"","filename":"figure3.png","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/1b90b715edb6fb340e1ca630.png"},{"id":94362566,"identity":"66e9431e-6e7a-4b16-82ae-1a24efbfd27e","added_by":"auto","created_at":"2025-10-27 13:05:13","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":1555192,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eROC curve analysis of the Logistic model. \u003c/strong\u003eA: training set; B: validation set; C: test set.Logistic, Logistic Regression.\u003c/p\u003e","description":"","filename":"figure4.png","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/614780daaf65c4e5d08908fb.png"},{"id":94362033,"identity":"0c6c5840-0599-4458-88d3-626a531bbef4","added_by":"auto","created_at":"2025-10-27 13:04:43","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":801004,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eAnalysis of curves related to the Logistic model. \u003c/strong\u003eA: Learning Curve; B: Calibration Curve; C: Decision Curve Analysis. Logistic Regression.\u003c/p\u003e","description":"","filename":"figure5.png","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/bd48f90b2ee156fcf96229c5.png"},{"id":94361935,"identity":"b13ca77c-d52e-493f-b43f-db4b4d887554","added_by":"auto","created_at":"2025-10-27 13:04:39","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":616285,"visible":true,"origin":"","legend":"\u003cp\u003eA: SHAP bee swarm visualization; B: Global ranking of feature importance; C: SHAP force plot corresponding to a patient diagnosed with urosepsis; D: SHAP force plot corresponding to a patient diagnosed with non-urosepsis.\u003c/p\u003e","description":"","filename":"figure6.png","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/684ee475bc441ff4472c2c3d.png"},{"id":94442486,"identity":"6845d975-0fe4-4247-af1a-cc567f2a7fa6","added_by":"auto","created_at":"2025-10-27 14:28:53","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":9032094,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7584146/v1/7ccc6ea3-b296-4435-8396-8d27e44bdf85.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Predicting Postoperative Sepsis Risk in Diabetic Urolithiasis Patients: A Multimodal Clinical Data-Driven Machine Learning Model","fulltext":[{"header":"Introduction","content":"\u003cp\u003eInfectious urosepsis is one of the most severe complications after surgery for urinary tract stone patients. Its rapid progression is often associated with high mortality rates and substantial medical costs, making it a central challenge in perioperative management. Diabetic patients, due to metabolic abnormalities and impaired immune function, are more susceptible to urinary tract infections (UTI), which can then progress to urosepsis[1]. Studies have shown[2] that in type 2 diabetic patients with upper urinary tract stones (UUTS), the incidence of urosepsis is 4.5%, with diabetes patients accounting for 34.8% of these cases. It is worth noting that in diabetic patients, the risk of postoperative infectious complications significantly increases after undergoing surgical treatments such as percutaneous nephrolithotomy (PCNL) or ureteroscopy (URSL)[3\u0026ndash;5]. Moreover, once diabetic patients develop urosepsis, their condition is more likely to deteriorate into septic shock, particularly in elderly patients[6].\u003c/p\u003e\u003cp\u003eHowever, despite the significantly increased risk of postoperative infection in diabetic patients with urinary stones, effective predictive tools for this high-risk group are still lacking. Traditional assessment methods often rely on single indicators or clinical experience[7], which makes it difficult to accurately capture the complex metabolic and immune status of diabetic patients. Existing risk scoring systems such as qSOFA, SIRS, and NEWS have lower sensitivity in this population, making them prone to missing high-risk individuals[8]. Therefore, there is an urgent need to explore more accurate predictive methods for postoperative infectious urosepsis risk in diabetic patients with urinary stones, in order to develop more personalized and precise treatment strategies, ultimately improving the patients' quality of life and survival rate.\u003c/p\u003e\u003cp\u003eIn recent years, machine learning (ML) has not only been able to autonomously identify new variables and their complex relationships from datasets[9], but also explain model decision logic through techniques like SHAP values[10], thus improving prediction credibility and clinical applicability. Its application in the medical field has rapidly expanded, showing great promise and is increasingly used in developing novel prognostic models for various diseases.\u003c/p\u003e\u003cp\u003eIn summary, this study aims to comprehensively analyze the multimodal clinical data of diabetic patients with urinary stones, identify significant predictive factors for postoperative infectious urosepsis risk, and develop and validate an ML prediction model using advanced ML techniques. This will provide a theoretical basis and decision support for early identification and precise intervention, promoting the establishment of individualized perioperative management strategies and improving patient prognosis.\u003c/p\u003e"},{"header":"Materials and Methods","content":"\u003cp\u003eThis study included 532 patients who were diagnosed with diabetes and underwent surgical treatment for upper urinary tract stones at the Sixth Affiliated Hospital of Guangxi Medical University between June 2018 and June 2023. The study was conducted in strict accordance with the ethical principles outlined in the Declaration of Helsinki, and all data were derived from real clinical cases. Informed consent was obtained from each patient or their authorized representative prior to sample collection. Inclusion criteria were as follows: (1) patients with a prior diagnosis of diabetes who were subsequently diagnosed with upper urinary tract stones at the Sixth Affiliated Hospital of Guangxi Medical University; (2) patients who received surgical treatment in accordance with the indications for surgical management of urinary stone disease as outlined in the 2015 European Association of Urology (EAU) Guidelines for Urolithiasis; (3) complete demographic and clinical examination data available; (4) age\u0026thinsp;\u0026ge;\u0026thinsp;18 years. Exclusion criteria included: (1) patients with an unclear diagnosis or without a history of diabetes; (2) patients with concomitant urinary system malformations; (3) patients with other systemic infectious diseases; (4) patients with malignant tumors; (5) patients with mental health disorders or impaired speech and communication abilities.\u003c/p\u003e\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\u003ch2\u003eClinical Data Collection and Feature Selection\u003c/h2\u003e\u003cp\u003eThe dataset used in this study comprises 532 cases of patients previously diagnosed with diabetes who underwent surgical treatment for upper urinary tract stones. It includes 164 feature variables, categorized as follows: (1) Demographic and vital sign data, including age, gender, BMI, heart rate, blood pressure, body temperature, etc.; (2) Inflammatory and infection markers, including CRP, PCT, IL-6, SAA, and urinary white blood cells; (3) Surgical-related information, including surgical methods, number of surgeries, ASA classification, and Barthel index; (4) Routine laboratory tests, including blood and urine tests, liver and kidney function, and coagulation function.\u003c/p\u003e\u003cp\u003eTo reduce the number of features to be tested across various classifiers, feature selection was performed. Initially, parameters with no significant differences between the two groups were excluded. Subsequently, feature selection was carried out using Lasso regression and the Boruta algorithm. Lasso regression is a statistical modeling method that combines variable selection with regularization, making it particularly suitable for high-dimensional data analysis. The Boruta algorithm, based on random forests, is particularly effective for identifying all relevant features associated with the target variable in high-dimensional data. In this study, Lasso regression and the Boruta algorithm were combined, with the intersection of the selected features from both methods used for final feature selection. This approach not only preserves predictive and relevant features but also avoids overlooking important nonlinear or interaction features. It provides a more stable, accurate, and interpretable feature set, while reducing the risk of overfitting. The selected features were then used for subsequent model training and analysis.\u003c/p\u003e\u003c/div\u003e\n\u003ch3\u003eStudy Design\u003c/h3\u003e\n\u003cp\u003eThe workflow of this study is briefly summarized in a flowchart, and the study cohort is systematically described(Figs.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e). Specifically, the data collected from the Sixth Affiliated Hospital of Guangxi Medical University were randomly divided into a training set (n\u0026thinsp;=\u0026thinsp;372, 70%) and a validation set (n\u0026thinsp;=\u0026thinsp;160, 30%). After feature selection, nine machine learning algorithms (ML) were used to construct the model in the training cohort based on 10-fold cross-validation, including logistic regression, extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), random forest (RF), adaptive boosting (AdaBoost), gradient boosting decision tree (GBDT), Gaussian naive Bayes (GNB), support vector machine (SVM), and K-nearest neighbors (KNN). These models were then evaluated for performance in the validation cohort. The models were comprehensively assessed, and the classifier with the best predictive performance was selected to build the final risk prediction model. Model evaluation metrics included accuracy, positive predictive value (PPV), negative predictive value (NPV), and others. Additionally, the model\u0026rsquo;s ability to predict the risk of postoperative infectious urosepsis was tested using receiver operating characteristic (ROC) curves, learning curves, calibration curves, and decision curve analysis (DCA). Finally, SHAP (SHapley Additive exPlanations) values were used to visualize the impact of key variables on the model's output, enhancing model interpretability and clinical applicability.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cdiv id=\"Sec5\" class=\"Section2\"\u003e\u003ch2\u003eStatistical Analysis\u003c/h2\u003e\u003cp\u003eAll data were analyzed using Python software (version 3.8), utilizing the glmnet (version 4.1), xgboost (version 2.0.1), lightgbm (version 3.2.1), and scikit-learn (version 1.1.3) packages. Normality tests were performed for quantitative data. Data that followed a normal distribution were expressed as mean\u0026thinsp;\u0026plusmn;\u0026thinsp;standard deviation and analyzed using the Student\u0026rsquo;s t-test. Data that did not follow a normal distribution were expressed as median and interquartile range (IQR) and analyzed using the Mann-Whitney U test. Categorical data were expressed as counts and percentages and analyzed using the chi-square test. All statistical tests were two-sided, with P values\u0026thinsp;\u0026lt;\u0026thinsp;0.05 considered statistically significant.\u003c/p\u003e\u003c/div\u003e"},{"header":"Results","content":"\u003cdiv id=\"Sec7\" class=\"Section2\"\u003e\u003ch2\u003ePatient Feature Selection\u003c/h2\u003e\u003cp\u003eAccording to the inclusion criteria, 532 patients who were previously diagnosed with diabetes and underwent surgical treatment for upper urinary tract stones were finally included. These patients were randomly divided into a training cohort (n\u0026thinsp;=\u0026thinsp;372) and a validation cohort (n\u0026thinsp;=\u0026thinsp;160), with a ratio of 7:3. Among the 164 parameters, 59 were significantly associated with the occurrence of postoperative infectious urosepsis (P\u0026thinsp;\u0026lt;\u0026thinsp;0.05) (Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e). Next, feature selection was performed using Lasso regression and the Boruta algorithm[11]. Lasso regression selected variables with non-zero coefficients (β\u0026thinsp;\u0026ne;\u0026thinsp;0), resulting in 5 features that met the criteria (Figs.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003eA-B), including p_IL_6, p_TP, p_PCT/p_ALB, p_T, and p_HR. The Boruta algorithm selected \"importance scores\" for each true feature that were significantly higher than all shadow features' Confirmed and Tentative indicators (yellow and green areas in the figure). A total of 16 features met the criteria (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003eC), including p_GGT, p_SAA, p_Lymph_WBC, p_Lymph, p_ALB, p_NLR, p_PLR, p_NLPR, p_SII, p_LCR, p_CRP/p_ALB, p_IL_6, p_PCT/p_ALB, p_T, p_HR, and p_procalcitonin.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eBiomarker Characteristics of Patients with non - sepsis and Sepsis\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"4\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eVariables\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003enon - sepsis (N\u0026thinsp;=\u0026thinsp;478)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003esepsis (N\u0026thinsp;=\u0026thinsp;54)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAge, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e58.00 [54.00;67.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e58.00 [53.00;64.75]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.427\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBMI, Mean (SD)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e24.37 (2.99)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e23.41 (3.21)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.039\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003etimes_operstion, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e2.00 [1.00;3.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e2.00 [1.00;3.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.838\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eT, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e36.60 [36.50;36.70]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e36.60 [36.30;36.70]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.912\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHR, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e73.00 [63.00;85.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e85.00 [71.00;97.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSBP, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e132.00 [123.00;145.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e124.00 [119.00;141.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eDBP, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e82.00 [76.00;89.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e79.00 [75.00;88.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.202\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSG, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.01 [1.00;1.01]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1.01 [1.00;1.01]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.764\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePH_value, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e6.00 [5.62;6.50]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e6.00 [5.50;7.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.836\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSED_RBC, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e95.00 [12.00;1670.25]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e62.50 [10.25;297.75]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.076\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSED_WBC, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e54.00 [17.08;221.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e217.50 [45.50;420.12]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.006\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSED_EC, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e5.00 [2.00;12.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e4.00 [2.00;10.75]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.237\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSED_casts, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.00 [0.00;1.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.00 [0.00;1.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.616\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSED_bacteria, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e24.00 [9.00;81.75]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e34.50 [15.50;202.25]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.119\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eU_conductivity, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e11.65 [8.60;14.60]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e10.60 [8.00;14.45]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.352\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eWBC, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e7.01 [6.02;8.43]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e6.88 [5.81;8.89]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.974\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNeut_WBC, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e61.25 [55.60;67.20]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e61.40 [56.70;68.15]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.457\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLymph_WBC, Mean (SD)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e27.23 (8.26)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e26.11 (7.89)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.328\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMono_WBC, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e6.60 [5.60;8.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e7.00 [5.25;7.97]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.808\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eEos_WBC, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e3.00 [2.00;4.70]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e3.35 [2.20;4.57]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.667\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBaso_WBC, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.60 [0.40;0.80]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.60 [0.50;0.80]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.341\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNeut, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e4.26 [3.43;5.34]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e4.23 [3.43;5.95]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.664\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLymph, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.88 [1.47;2.28]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1.83 [1.44;2.13]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.289\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMono, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.46 [0.37;0.60]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.48 [0.34;0.60]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.908\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eEos, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.21 [0.13;0.32]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.20 [0.15;0.29]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.876\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBaso, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.04 [0.03;0.06]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.04 [0.03;0.07]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.484\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRBC, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e4.42 [4.00;4.86]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e4.21 [3.89;4.60]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.062\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHGB, Mean (SD)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e124.67 (19.62)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e115.83 (18.25)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHCT, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.38 [0.34;0.41]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.35 [0.32;0.39]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.002\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMCV, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e87.40 [82.90;90.38]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e87.05 [83.08;89.80]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.366\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMCH, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e29.10 [27.30;30.30]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e28.90 [26.05;29.67]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.135\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMCHC, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e330.70 [321.00;340.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e328.00 [316.25;336.75]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.051\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRDW, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e12.80 [12.20;13.70]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e13.05 [12.43;13.88]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.126\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePLT, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e261.00 [216.00;312.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e292.00 [240.00;330.75]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.037\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMPV, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e9.70 [9.30;10.20]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e9.45 [9.20;10.10]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.105\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eB_PCT, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.25 [0.21;0.30]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.28 [0.24;0.31]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.063\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBUA, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e367.75 [292.88;438.75]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e345.50 [287.25;428.70]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.306\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBUN, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e5.88 [4.67;7.69]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e5.43 [4.26;8.05]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.268\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eScr, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e103.75 [81.52;135.98]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e102.00 [80.25;134.75]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.803\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eeGFR, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e66.81 [47.52;85.77]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e64.50 [49.96;81.22]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.962\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHCO3, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e23.50 [21.80;25.10]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e22.85 [20.68;24.54]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.139\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ebeta2_MG, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e2.57 [2.05;3.53]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e2.83 [2.31;4.34]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.043\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCysC, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.20 [1.05;1.56]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1.27 [1.05;1.60]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.446\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTP, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e70.90 [67.80;74.20]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e71.30 [68.93;76.68]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.21\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eALB, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e39.90 [37.80;42.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e38.80 [36.05;41.30]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.029\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGLB, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e30.70 [27.90;34.53]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e33.65 [29.15;37.60]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.004\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eALB_GLB, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.30 [1.10;1.50]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1.20 [1.00;1.30]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBIL, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e7.10 [5.20;9.47]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e6.80 [5.20;10.83]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.794\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eDBIL, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e3.30 [2.60;4.35]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e3.35 [2.60;4.77]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.498\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eI_Bil, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e3.70 [2.50;5.20]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e3.70 [2.40;5.80]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.926\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGPT, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e15.00 [11.00;21.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e16.00 [10.10;23.50]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.894\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGOT, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e16.70 [13.22;20.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e15.95 [13.03;23.50]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.606\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eALP, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e71.00 [60.00;85.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e75.50 [61.25;89.75]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.299\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGGT, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e27.00 [18.00;38.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e29.50 [19.00;43.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.37\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTBA, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e4.25 [2.60;6.80]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e3.70 [2.00;7.08]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.398\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCRP, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e3.01 [1.39;7.84]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e3.90 [2.42;11.29]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.04\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eK, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e3.91 [3.64;4.17]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e3.97 [3.70;4.25]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.272\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCa, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e2.30 [2.23;2.37]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e2.30 [2.22;2.37]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.981\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePT, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e10.90 [10.41;11.60]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e10.95 [10.66;12.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.103\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eINR, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.95 [0.90;1.01]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.95 [0.92;1.05]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.095\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePTA, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e115.50 [101.25;128.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e111.50 [91.50;123.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.043\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTT, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e18.60 [17.90;19.40]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e18.60 [17.45;19.55]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.455\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAPTT, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e25.70 [23.50;28.37]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e26.07 [23.50;28.35]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.426\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePF, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e3.36 [2.90;4.22]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e3.54 [2.93;4.90]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.106\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNLR, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e2.22 [1.71;3.06]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e2.29 [1.73;3.19]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.467\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePLR, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e134.93 [107.96;180.56]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e155.05 [121.07;206.97]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.016\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLMR, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e4.13 [3.08;5.24]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e3.87 [2.89;4.99]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.42\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eELR, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.11 [0.07;0.18]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.12 [0.08;0.18]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.36\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003edNLR, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.58 [1.26;2.06]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1.58 [1.31;2.14]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.472\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNLPR, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.01 [0.01;0.01]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.01 [0.01;0.01]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.59\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSII, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e580.54 [409.60;829.07]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e696.80 [436.47;1022.01]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.101\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAISI, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e274.11 [168.97;458.34]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e276.18 [203.48;557.52]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.287\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSIRI, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.01 [0.68;1.67]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1.00 [0.79;1.92]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.678\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLCR, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.66 [0.25;1.42]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.42 [0.18;0.84]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.028\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCRP_ALB, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.08 [0.03;0.20]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.10 [0.06;0.32]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.031\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_CRP, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e3.07 [0.86;8.22]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e21.98 [2.31;53.80]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_SAA, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e10.00 [6.00;20.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e23.00 [10.00;72.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_procalcitonin, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.05 [0.03;0.08]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.41 [0.09;14.23]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_IL_6, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e14.65 [7.70;32.80]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e71.35 [27.74;419.10]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_WBC, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e7.92 [6.36;9.98]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e10.37 [6.31;13.36]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_Neut_WBC, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e69.50 [61.50;78.47]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e79.55 [66.45;89.45]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_Lymph_WBC, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e20.85 [14.50;28.75]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e11.70 [6.82;23.10]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_Mono_WBC, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e5.70 [4.20;6.90]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e5.60 [2.75;7.45]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.98\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_Eos_WBC, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.70 [0.80;3.20]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1.50 [0.23;2.80]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.121\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_Baso_WBC, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.40 [0.30;0.60]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.40 [0.20;0.50]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.299\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_Neut, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e5.47 [4.07;7.35]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e7.74 [4.43;10.95]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.002\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_Lymph, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.56 [1.13;2.10]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1.09 [0.72;1.47]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_Mono, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.42 [0.28;0.57]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.48 [0.26;0.74]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.145\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_Eos, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.13 [0.06;0.24]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.14 [0.02;0.23]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.237\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_Baso, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.03 [0.02;0.05]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.04 [0.02;0.05]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.449\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_RBC, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e4.20 [3.81;4.65]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e3.76 [3.38;4.35]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_HGB, Mean (SD)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e119.45 (18.54)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e104.81 (20.99)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_HCT, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.36 [0.33;0.40]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.31 [0.27;0.37]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_MCV, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e87.50 [83.60;90.77]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e86.65 [80.32;88.55]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.076\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_MCH, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e29.10 [27.30;30.30]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e29.00 [26.25;29.78]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.142\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_MCHC, Mean (SD)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e329.34 (14.99)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e328.39 (13.89)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.638\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_RDW, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e12.80 [12.20;13.70]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e13.20 [12.53;14.60]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.017\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_PLT, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e241.50 [201.00;300.75]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e259.50 [193.25;309.25]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.705\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_MPV, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e9.70 [9.30;10.30]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e9.90 [9.30;10.30]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.503\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_PCT, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.24 [0.20;0.29]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.25 [0.21;0.31]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.7\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_BUA, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e267.50 [202.48;341.40]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e255.50 [188.20;315.20]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.238\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_BUN, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e4.60 [3.50;6.03]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e4.75 [3.69;6.30]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.753\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_Scr, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e100.00 [78.00;132.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e107.00 [80.00;141.50]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.25\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_eGFR, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e67.09 [48.27;89.05]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e65.48 [32.54;81.62]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.189\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_HCO3, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e22.70 [20.80;24.50]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e21.30 [19.92;23.58]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.014\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_beta2_MG, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e2.42 [1.92;3.38]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e2.83 [2.20;5.01]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.008\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_TP, Mean (SD)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e65.80 (5.85)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e63.41 (7.47)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.036\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_ALB, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e36.00 [33.45;38.55]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e33.20 [30.18;36.20]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_GLB, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e29.50 [26.80;32.45]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e29.85 [25.58;33.50]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.901\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_ALBGLB, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.20 [1.10;1.40]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1.10 [0.90;1.33]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_BIL, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e9.00 [6.55;12.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e9.75 [7.15;14.80]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.142\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_DBIL, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e4.20 [3.20;5.50]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e5.00 [4.00;6.90]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.003\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_I_Bil, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e4.80 [3.20;6.70]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e4.75 [3.03;6.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.551\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_GPT, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e12.50 [9.00;18.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e13.50 [8.85;21.52]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.403\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_GOT, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e15.00 [12.00;18.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e17.50 [13.00;24.08]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.016\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_ALP, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e63.00 [52.50;75.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e62.00 [49.50;78.50]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.855\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_GGT, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e24.80 [17.00;36.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e35.00 [16.75;79.50]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.017\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_TBA, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.90 [1.10;3.50]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e2.60 [1.40;5.15]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.013\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_K, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e3.89 [3.59;4.15]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e3.66 [3.39;3.88]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_Ca, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e2.19 [2.12;2.27]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e2.12 [2.04;2.23]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.002\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_PT, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e11.70 [11.28;12.40]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e12.40 [11.50;12.90]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.092\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_INR, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.02 [0.98;1.08]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1.08 [1.00;1.13]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.087\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_PTA, Mean (SD)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e102.64 (17.46)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e91.67 (17.64)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.035\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_TT, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e18.25 [17.40;19.22]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e18.10 [17.25;19.80]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.838\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_APTT, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e26.30 [23.78;29.05]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e25.40 [22.00;28.50]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.601\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_PF, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e3.42 [2.87;4.14]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e3.24 [2.98;4.77]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.785\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_NLR, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e3.36 [2.16;5.35]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e6.88 [2.82;12.89]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_PLR, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e152.21 [109.85;230.10]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e230.65 [157.83;360.10]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_LMR, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e4.16 [2.84;5.92]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e2.67 [1.51;3.95]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_ELR, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.08 [0.04;0.14]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.08 [0.04;0.18]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.427\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_dNLR, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e2.28 [1.60;3.65]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e3.90 [1.98;8.45]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_NLPR, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.01 [0.01;0.02]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.02 [0.01;0.06]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_SII, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e813.30 [503.18;1427.04]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1864.08 [791.33;3020.20]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_AISI, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e329.31 [189.52;556.50]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e689.22 [266.96;1807.54]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_LCR, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.55 [0.16;1.75]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.04 [0.01;0.70]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_SIRI, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.31 [0.77;2.24]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e2.47 [1.11;5.76]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_CRPp_ALB, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.08 [0.02;0.24]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.84 [0.07;1.91]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_PCTp_ALB, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01 [\u0026lt;\u0026thinsp;0.01;\u0026lt;0.01]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.02 [\u0026lt;\u0026thinsp;0.01;0.39]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eWBCp_WBC, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.92 [0.72;1.11]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.81 [0.58;1.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.014\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_T, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e36.80 [36.70;36.90]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e38.55 [36.82;39.18]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_SBP, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e131.00 [121.00;146.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e126.00 [114.50;143.50]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.09\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_DBP, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e78.00 [72.00;86.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e78.00 [68.00;87.50]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.682\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_HR, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e76.00 [68.00;83.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e92.50 [84.25;102.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_RR, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e20.00 [18.00;20.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e20.00 [19.25;20.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBarthel_Index, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e40.00 [30.00;85.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e65.00 [30.00;88.75]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.206\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eVTE, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e2.00 [1.00;3.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e2.00 [1.50;3.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.515\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSurgery, N (%):\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePCNL\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e172 (35.98%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e30 (55.56%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRIRS\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e128 (26.78%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e17 (31.48%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eOthers\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e178 (37.24%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e7 (12.96%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSex, N (%):\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.202\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003emale\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e217 (45.40%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e30 (55.56%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003efemale\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e261 (54.60%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e24 (44.44%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRR, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e20.00 [20.00;20.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e20.00 [20.00;20.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.907\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eU_culture, N (%):\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.857\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e423 (88.49%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e47 (87.04%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e9 (1.88%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1 (1.85%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTRUE\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e46 (9.62%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e6 (11.11%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eU_LEU, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.00 [0.00;4.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e3.50 [1.00;4.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.003\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eU_NIT, N (%):\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.116\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e448 (93.72%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e50 (92.59%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e15 (3.14%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0 (0.00%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e15 (3.14%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e4 (7.41%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eU_PRO, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.00 [0.00;1.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.00 [0.00;1.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.535\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eU_GLU, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.00 [0.00;2.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.00 [0.00;0.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.088\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eU_URO, N (%):\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e472 (98.74%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e54 (100.00%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e2 (0.42%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0 (0.00%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e3 (0.63%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0 (0.00%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1 (0.21%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0 (0.00%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eU_BIL, N (%):\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e473 (98.95%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e54 (100.00%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e2 (0.42%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0 (0.00%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e3 (0.63%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0 (0.00%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eOB, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e2.00 [0.00;3.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1.00 [0.00;2.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.046\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ep_CNS, N (%):\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.697\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e432 (90.38%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e48 (88.89%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e2 (0.42%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0 (0.00%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e44 (9.21%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e6 (11.11%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eASA, N (%):\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.85\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e20 (4.18%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e3 (5.56%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e439 (91.84%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e49 (90.74%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e19 (3.97%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e2 (3.70%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMorse, Median [Q1-Q3]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e4.00 [4.00;5.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e4.00 [4.00;5.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.628\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"4\"\u003eBMI, Body Mass Index; T, Temperature;HR, Heart Rate; SBP, Systolic Blood Pressure; DBP, Diastolic Blood Pressure; SG, Specific Gravity; SED_RBC, Sediment Red Blood Cells, SED_WBC, Sediment White Blood Cells; SED_EC, Sediment Epithelial Cells; SED_casts, Sediment Casts; SED_bacteria, Sediment Bacteria; U_conductivity, Urine Conductivity; WBC, White Blood Cell Count; Neut_WBC, Neutrophil WBC; Lymph_WBC, Lymphocyte WBC; Mono_WBC, Monocyte WBC; Eos_WBC, Eosinophil WBC; Baso_WBC, Basophil WBC; Neut, Neutrophil Percentage; Lymph, Lymphocyte Percentage; Mono, Monocyte Percentage; Eos, Eosinophil Percentage; Baso, Basophil Percentage; RBC, Red Blood Cell Count; HGB, Hemoglobin; HCT, Hematocrit; MCV, Mean Corpuscular Volume; MCH, Mean Corpuscular Hemoglobin; MCHC, Mean Corpuscular Hemoglobin Concentration; RDW, Red Cell Distribution Width; PLT, Platelet Count; MPV, Mean Platelet Volume; B_PCT, Blood Platelet Count; BUA, Blood Uric Acid; BUN, Blood Urea Nitrogen; Scr, Serum Creatinine; eGFR, Estimated Glomerular Filtration Rate; HCO3, Bicarbonate; beta2_MG, Beta-2 Microglobulin; CysC, Cystatin C; TP, Total Protein; ALB, Albumin; GLB, Globulin; ALB_GLB, Albumin to Globulin Ratio; BIL, Total Bilirubin; DBIL, Direct Bilirubin; I_Bil, Indirect Bilirubin; GPT, Glutamic Pyruvic Transaminase; GOT, Glutamic Oxaloacetic Transaminase; ALP, Alkaline Phosphatase; GGT, Gamma-Glutamyl Transferase; TBA, Total Bile Acids; CRP, C-Reactive Protein; K, Potassium; Ca, Calcium; PT, Prothrombin Time; INR, International Normalized Ratio; PTA, Prothrombin Time Activity; TT, Thrombin Time; APTT, Activated Partial Thromboplastin Time; PF, Platelet Factor; NLR, Neutrophil to Lymphocyte Ratio; PLR, Platelet to Lymphocyte Ratio; LMR, Lymphocyte to Monocyte Ratio; ELR, Eosinophil to Lymphocyte Ratio; dNLR, Derived Neutrophil to Lymphocyte Ratio; NLPR, Neutrophil to Lymphocyte and Platelet Ratio; SII, Systemic Inflammatory Index; AISI, Adjusted Inflammatory Score Index; SIRI, Systemic Immune-Inflammatory Index; LCR, Lymphocyte to Creatinine Ratio; CRP_ALB, C-Reactive Protein to Albumin Ratio; p_CRP, Procalcitonin; p_SAA, Serum Amyloid A; p, postoperative.\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eAfter considering both Lasso regression and Boruta algorithm-selected features, four key predictors were initially selected: p_IL_6, p_PCT/p_ALB, p_T, and p_HR. These four predictor variables were then subjected to Pearson correlation analysis (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003eD). The results showed that there was no strong correlation between the feature variables (r\u0026thinsp;\u0026lt;\u0026thinsp;0.7), indicating that the features were relatively independent and did not redundantly express the same information. This is beneficial for improving the model's generalization ability, robustness, and interpretability. Therefore, these four feature variables were ultimately included (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003eE).\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e\u003ch2\u003eComparison of the Performance of 9 Machine Learning Algorithms\u003c/h2\u003e\u003cp\u003eAll patients were randomly divided into a training cohort (70%) and a validation cohort (30%). To reduce the instability and overfitting of the prediction results, 10-fold cross-validation was used to determine the model\u0026rsquo;s average prediction accuracy. Model performance was comprehensively evaluated using AUC, accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), F1 score, and Kappa value[12]. The results showed that the nine machine learning models demonstrated good discrimination ability in both the training and validation cohorts(Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e). Among them, the XGBoost, LightGBM, RandomForest, AdaBoost, and GBDT models had an AUC value of 1.00 in the training cohort, while their AUC values in the validation cohort were 0.86, 0.84, 0.83, 0.77, and 0.83, respectively, suggesting potential overfitting. On the other hand, the logistic regression, GNB, KNN, and SVM models exhibited more consistent AUC and accuracy between the training and validation cohorts, indicating no significant overfitting. Among these, logistic regression showed the best performance in predicting the risk of postoperative infectious urosepsis in diabetic patients with urinary stones, particularly in terms of AUC, demonstrating a significant advantage (Figs.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003ea-b). Therefore, we concluded that the logistic regression model outperformed other machine learning models in predicting the risk of postoperative infectious urosepsis and selected it as our final predictive model.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003ePerformance of Each Model in the Training and Validation Cohort.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"11\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c10\" colnum=\"10\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c11\" colnum=\"11\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCohort\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eModels\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eAUC(95%CI)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003ecutoff(95%CI)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eACC(95%CI)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eTPR(95%CI)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003eTNR(95%CI)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c8\"\u003e\u003cp\u003ePPV(95%CI)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c9\"\u003e\u003cp\u003eNPV(95%CI)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c10\"\u003e\u003cp\u003eF1 Score(95%CI)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c11\"\u003e\u003cp\u003eKappa(95%CI)\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"8\" rowspan=\"9\"\u003e\u003cp\u003eTraining\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003elogistic\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.91 (0.84\u0026ndash;0.97)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.16(0.14\u0026ndash;0.17)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.91(0.90\u0026ndash;0.92)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.79(0.77\u0026ndash;0.81)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.92(0.91\u0026ndash;0.94)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.59(0.55\u0026ndash;0.62)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0.97(0.97\u0026ndash;0.97)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.67(0.65\u0026ndash;0.69)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e0.62(0.59\u0026ndash;0.65)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eXGBoost\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e1.00 (NaN-NaN)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.67(0.64\u0026ndash;0.71)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLightGBM\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e1.00 (NaN-NaN)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.9(0.88\u0026ndash;0.91)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eRandomForest\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e1.00 (NaN-NaN)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.53(0.50\u0026ndash;0.56)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eAdaBoost\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e1.00 (NaN-NaN)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.5(0.50\u0026ndash;0.50)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e1.0(0.99-1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e1.0(0.99-1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.98(0.95-1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.99(0.97-1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e0.99(0.97-1.00)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eGBDT\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e1.00 (NaN-NaN)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.82(0.79\u0026ndash;0.84)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eGNB\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.90 (0.83\u0026ndash;0.96)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.0(0.00\u0026ndash;0.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.87(0.86\u0026ndash;0.88)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.83(0.81\u0026ndash;0.85)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.87(0.86\u0026ndash;0.89)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.47(0.45\u0026ndash;0.49)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0.98(0.97\u0026ndash;0.98)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.6(0.58\u0026ndash;0.62)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e0.53(0.51\u0026ndash;0.55)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eKNN\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.97 (0.95\u0026ndash;0.99)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.2(0.20\u0026ndash;0.20)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.85(0.84\u0026ndash;0.86)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.83(0.82\u0026ndash;0.84)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.44(0.42\u0026ndash;0.46)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e1.0(1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.62(0.60\u0026ndash;0.63)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e0.54(0.52\u0026ndash;0.56)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSVM\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.87 (0.77\u0026ndash;0.96)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.1(0.08\u0026ndash;0.12)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.93(0.93\u0026ndash;0.94)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.75(0.73\u0026ndash;0.77)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.96(0.95\u0026ndash;0.97)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.72(0.67\u0026ndash;0.76)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0.97(0.96\u0026ndash;0.97)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.73(0.71\u0026ndash;0.75)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e0.69(0.67\u0026ndash;0.72)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"8\" rowspan=\"9\"\u003e\u003cp\u003eValidation\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003elogistic\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.90 (NaN-NaN)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.16(0.14\u0026ndash;0.17)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.89(0.85\u0026ndash;0.92)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.74(0.58\u0026ndash;0.90)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.91(0.87\u0026ndash;0.94)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.54(0.44\u0026ndash;0.63)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0.96(0.94\u0026ndash;0.99)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.6(0.49\u0026ndash;0.72)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e0.54(0.41\u0026ndash;0.67)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eXGBoost\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.86 (NaN-NaN)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.67(0.64\u0026ndash;0.71)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.94(0.93\u0026ndash;0.95)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.61(0.47\u0026ndash;0.74)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.98(0.97-1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.88(0.79\u0026ndash;0.98)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0.95(0.94\u0026ndash;0.97)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.68(0.60\u0026ndash;0.77)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e0.65(0.56\u0026ndash;0.74)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLightGBM\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.84 (NaN-NaN)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.9(0.88\u0026ndash;0.91)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.93(0.90\u0026ndash;0.95)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.42(0.25\u0026ndash;0.60)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e1.0(0.99-1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003enan(NaN-NaN)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0.93(0.91\u0026ndash;0.95)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003enan(NaN-NaN)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e0.51(0.31\u0026ndash;0.72)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eRandomForest\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.83 (NaN-NaN)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.53(0.50\u0026ndash;0.56)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.94(0.91\u0026ndash;0.96)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.62(0.44\u0026ndash;0.81)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.98(0.96-1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.89(0.78\u0026ndash;1.01)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0.95(0.93\u0026ndash;0.98)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.68(0.54\u0026ndash;0.82)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e0.65(0.51\u0026ndash;0.80)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eAdaBoost\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.77 (NaN-NaN)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.5(0.50\u0026ndash;0.50)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.92(0.88\u0026ndash;0.96)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.52(0.28\u0026ndash;0.76)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.97(0.95-1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003enan(NaN-NaN)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0.94(0.91\u0026ndash;0.97)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003enan(NaN-NaN)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e0.52(0.27\u0026ndash;0.78)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eGBDT\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.83 (NaN-NaN)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.82(0.79\u0026ndash;0.84)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.93(0.91\u0026ndash;0.96)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.48(0.29\u0026ndash;0.68)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.99(0.98-1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003enan(NaN-NaN)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0.94(0.91\u0026ndash;0.96)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003enan(NaN-NaN)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e0.55(0.33\u0026ndash;0.76)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eGNB\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.89 (NaN-NaN)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.0(0.00\u0026ndash;0.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.86(0.82\u0026ndash;0.90)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.78(0.64\u0026ndash;0.91)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.87(0.84\u0026ndash;0.91)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.46(0.36\u0026ndash;0.56)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0.97(0.95\u0026ndash;0.99)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.57(0.46\u0026ndash;0.68)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e0.49(0.37\u0026ndash;0.62)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eKNN\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.82 (NaN-NaN)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.2(0.20\u0026ndash;0.20)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.8(0.77\u0026ndash;0.84)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.71(0.56\u0026ndash;0.86)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.82(0.78\u0026ndash;0.85)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.34(0.28\u0026ndash;0.41)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0.96(0.93\u0026ndash;0.98)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.45(0.37\u0026ndash;0.54)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e0.35(0.26\u0026ndash;0.45)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSVM\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.85 (NaN-NaN)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.1(0.08\u0026ndash;0.12)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.91(0.88\u0026ndash;0.93)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.71(0.56\u0026ndash;0.86)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.93(0.90\u0026ndash;0.96)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.62(0.51\u0026ndash;0.74)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0.96(0.94\u0026ndash;0.98)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.63(0.53\u0026ndash;0.73)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e0.58(0.47\u0026ndash;0.69)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"11\"\u003eROC, receiver operating characteristic curve; Logistic, Logistic Regression; XGBoost, Extreme Gradient Boosting; LightGBM, Light Gradient Boosting Machine; AdaBoost, Adaptive Boosting;GBDT, Gradient Boosting Decision Tree; GNB, Gaussian Naive Bayes; KNN, K-Nearest Neighbor;SVM, Support Vector Machine.\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\n\u003ch3\u003eBest Model Performance\u003c/h3\u003e\n\u003cp\u003eGiven that the logistic regression model performed excellently in the initial modeling stage, we further validated its generalizability and robustness by randomly dividing the 532 patients into training, validation, and testing sets in a 4:4:2 ratio. Subsequently, 10-fold cross-validation was conducted on the training and validation cohorts, yielding average AUC values of 0.92 and 0.90, respectively. Based on these results, we further evaluated the model on an independent testing cohort, achieving an AUC of 0.87 (Figs.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003ea-c). These results indicate that the model maintained good predictive performance across different datasets, demonstrating strong generalizability and robustness.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eTo assess the model's performance and verify its clinical significance, we evaluated the model using learning curves, calibration curves, and decision curve analysis[13\u0026ndash;15]. The learning curve results showed that the model fit well and remained stable between the training and validation cohorts (Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003ea), avoiding both underfitting and overfitting. The calibration curve further confirmed that the predicted probabilities from the logistic regression model closely matched the actual probabilities (Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003eb), indicating that the model has high accuracy in probabilistic prediction. Furthermore, decision curve analysis demonstrated that the postoperative infectious urosepsis risk assessment model provided significant clinical net benefit within a threshold range of 5% to 90%, further validating its reliability and potential clinical application as a predictive tool (Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003ec).\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\n\u003ch3\u003eModel Interpretability\u003c/h3\u003e\n\u003cp\u003eA major limitation of machine learning is its difficulty in providing direct interpretability, which is often unacceptable in clinical practice[16]. To address this issue and assess the contribution of each feature to the prediction, we used SHAP analysis to interpret the logistic regression model[17]. The results showed that, among the four feature variables, p_T exhibited the highest SHAP value distribution and was the most influential predictor (Figs.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e6\u003c/span\u003ea-b). To further elucidate the decision-making process in individual cases, additional analysis revealed that in high-risk cases, elevated values of p_T and p_HR were the main drivers of increased risk (Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e6\u003c/span\u003ec). In contrast, in low-risk cases, lower levels of these variables led to reduced risk estimates (Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e6\u003c/span\u003ed). Overall, SHAP analysis provided both global and local interpretability, confirming that the model relies on clinically reasonable features, thereby enhancing its credibility and practical application potential in perioperative infection risk assessment.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e"},{"header":"Discussion","content":"\u003cp\u003eThe risk of postoperative sepsis is significantly increased in diabetic patients with urinary stones. Hyperglycemic conditions impair immune function, increasing susceptibility to infections[18]. Additionally, factors such as the complexity of the stones and surgical trauma further elevate the risk of postoperative urosepsis[19]. In this study, we constructed an interpretable risk prediction model for postoperative infectious urosepsis by incorporating four core predictive factors\u0026mdash;p_IL_6, p_PCT/p_ALB, p_T, and p_HR\u0026mdash;using multimodal clinical data and applying LASSO regression and Boruta algorithms. The results showed that the logistic regression model outperformed the other nine machine learning methods, with excellent performance in terms of prediction accuracy, sensitivity, and specificity. This model provides a valuable tool for early identification of high-risk patients and helps develop more personalized management strategies, ultimately improving clinical decision-making.\u003c/p\u003e\u003cp\u003ePrevious studies have reported that factors influencing the risk of postoperative urosepsis include specific stone components, diabetes, surgical complexity, and metabolic abnormalities in patients[20]. Notably, diabetes itself can be an independent predictor of postoperative sepsis[21]. Therefore, timely assessment of the risk of infectious urosepsis following surgery for stones in diabetic patients, and the implementation of preventive measures, can help reduce the incidence of postoperative infections and optimize resource allocation, thereby decreasing unnecessary treatments and hospitalization costs and improving healthcare efficiency.\u003c/p\u003e\u003cp\u003eBefore the widespread application of artificial intelligence, nomograms were commonly used as clinical disease prediction models[22\u0026ndash;24]. Yang et al. developed a nomogram that integrates renal pelvic pressure to predict the probability of urosepsis after percutaneous nephrolithotomy (PCNL), incorporating clinical features such as single kidney[25], nitrite-positive urine, surgery duration\u0026thinsp;\u0026ge;\u0026thinsp;75 minutes, recurrent urinary tract infections, and diabetes history. The AUC value in the training cohort was 0.887, and in the validation cohort, it was 0.864. However, nomograms have certain limitations, such as model overfitting, which can reduce prediction accuracy, and their susceptibility to confounding factors. Consequently, these traditional models are gradually being replaced by machine learning-based models.\u003c/p\u003e\u003cp\u003e To our knowledge, we have conducted a comprehensive review of multimodal clinical data, including demographics, vital signs, inflammation and infection indicators, surgical information, and routine laboratory tests, covering 164 clinical multimodal features. The interpretable risk prediction model for postoperative infectious urosepsis we constructed is the most comprehensive study on postoperative urosepsis prediction to date. The AUC values of this model were 0.916 in the training cohort, 0.903 in the validation cohort, and 0.866 in the test cohort, with model performance validated through learning curves, calibration curves, and decision curves. Using the SHAP values of the machine learning model, we were able to explain and visualize the prediction results. The most important variables were p_T, p_HR, p_IL_6, and p_PCT/p_ALB. Previous studies have confirmed that p_T, p_HR, p_IL_6, and p_PCT/p_ALB are risk factors for postoperative infectious urosepsis. Research has shown that specific thresholds of postoperative heart rate are significantly associated with the risk of sepsis[26\u0026ndash;27]. For example, patients with a P wave less than 103 milliseconds or a PR interval less than 157 milliseconds have an increased risk of postoperative sepsis by 2.06 or 2.33 times, respectively. Increased temperature combined with CRP or PCT levels has a specificity of 87.5% for predicting urosepsis[28]. Postoperative IL-6 and p_PCT/p_ALB have been identified as early biomarkers for urosepsis[29]. IL-6 reflects the intensity of the inflammatory response, while p_PCT/p_ALB integrates information on infection and metabolic status, reflecting the balance between inflammation and nutritional status. Both, in combination with other indicators, can optimize prediction models[30\u0026ndash;31], especially in diabetic patients with upper urinary tract stones, as their immune systems may be more vulnerable. An increase in this ratio helps in the early detection of the risk of infectious urosepsis.\u003c/p\u003e\u003cp\u003eHowever, despite the potential clinical application value, several limitations should be considered. First, this study was conducted in a single clinical research center in China with a relatively small sample size, and there may be regional biases. This could limit the generalizability of the model. Second, as this is a retrospective study, prospective cohort studies in more external hospital datasets are needed to validate the model\u0026rsquo;s external validity. Additionally, more rigorous cross-validation strategies should be employed to optimize its generalizability.\u003c/p\u003e\u003cp\u003eIn conclusion, this study developed an interpretable machine learning model using multimodal clinical data for the risk assessment of postoperative infectious urosepsis in diabetic patients with urinary stones. The results show that this model has high accuracy and interpretability, effectively helping clinicians identify high-risk patients and providing a basis for personalized treatment. However, the study has certain limitations, and future research should further validate the model's generalizability through prospective multicenter studies.\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003cp\u003eWe extend our deepest appreciation to all study participants whose trust and dedication made this research possible.\u003c/p\u003e\n"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eAuthors\u0026rsquo; contributions\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eConception and design: Fubo Wang.\u003c/p\u003e\n\u003cp\u003eData acquisition: Dongwei Pan, Zuheng Wang\u003c/p\u003e\n\u003cp\u003eData analysis and interpretation: Dianyu Wang, Zequn Su\u003c/p\u003e\n\u003cp\u003eDrafting the manuscript: Dongwei Pan, Zuheng Wang\u003c/p\u003e\n\u003cp\u003eCritical revision of the manuscript for scientific and factual content: Fubo Wang, Junyi Chen\u003c/p\u003e\n\u003cp\u003eStatistical analysis:Chunmeng Wei, Junhao Mi, Mingda Wang\u003c/p\u003e\n\u003cp\u003eSupervision: Fubo Wang\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis research received financial support from two funding sources: first, a grant (No. 82372828, principal investigator: F.W.) from the National Natural Science Foundation of China (NSFC); second, a grant (No. 2023GXNSFFA026003, principal investigator: F.W.) for the Science Foundation for Distinguished Young Scholars of Guangxi, affiliated with Guangxi Medical University.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData availability\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAny inquiries regarding the data and materials should be directed to the corresponding authors.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthics Approval and Consent to Participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eApproval statement\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe study was approved by the Ethics Committee of Guangxi Medical University. Clinical trial number: ChiCTR2400079409 on January 3, 2024 .\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAccordance statement\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study strictly adhered to the ethical principles outlined in the Declaration of Helsinki, ensuring that all data were derived from actual clinical cases.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eInformed Consent statement\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eInformed consent was obtained from each patient or their legal representative before sample collection.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for Publication\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting Interests\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors declare that they have no competing interests.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eGao C, Liu J, Wang D, Liu M, Qiu J. Risk factors and an optimized prediction model for urosepsis in diabetic patients with upper urinary tract stones. \u003cem\u003eSci Rep\u003c/em\u003e. 2025;15(1):8183.\u003c/li\u003e\n\u003cli\u003eWei J, Zeng R, Liang R, et al. Construction and validation of a nomogram prediction model for the progression to septic shock in elderly patients with urosepsis. \u003cem\u003eHeliyon\u003c/em\u003e. 2024;10(11):e32454.\u003c/li\u003e\n\u003cli\u003eSun H, Chen Z. Integration of minimally invasive techniques and interventional therapy: application of percutaneous nephrolithotomy in patients with upper urinary tract stones and an analysis of risk factors for postoperative bleeding. \u003cem\u003eFront Med (Lausanne)\u003c/em\u003e. 2025;12:1556224.\u003c/li\u003e\n\u003cli\u003eYing Z, Ming S, Yang R, et al. Comparison of safety and efficacy of negative pressure aspiration assisted retrograde intrarenal surgery and traditional percutaneous nephrolithotomy in the treatment of upper urinary tract stones larger than 2 cm: a systematic review and meta-analysis. \u003cem\u003eInt J Surg\u003c/em\u003e. 2025;111(5):3613-3628.\u003c/li\u003e\n\u003cli\u003eYu W, Yu F, Wang Y, Tang T, Huang X, Wang L. Efficacy and Postoperative Infection following Super Mini Percutaneous Nephrolithotomy \u003cem\u003evs\u003c/em\u003e Flexible Ureteroscopy for Diabetic Nephrolithiasis: A Comparative Analysis and Risk Factors for Postoperative Infectious Complications. \u003cem\u003eJ Endourol\u003c/em\u003e. 2024;38(10):1082-1091.\u003c/li\u003e\n\u003cli\u003eAlhamad FS, Alathel A, Aljaafri ZA, et al. Predictors of Urosepsis Post Percutaneous Nephrolithotomy at King Abdulaziz Medical City, Riyadh. \u003cem\u003eCureus\u003c/em\u003e. 2023;15(5):e39542.\u003c/li\u003e\n\u003cli\u003eBerman R, Lee J, Balasubramanian A, Shah O. The Association of Perioperative Glycated Hemoglobin (Hemoglobin A1C) and the Risk of Sepsis after Ureteroscopy with Laser Lithotripsy. \u003cem\u003eJ Endourol\u003c/em\u003e. 2025;39(6):549-555.\u003c/li\u003e\n\u003cli\u003eLiu Y, Sun Q, Long H, et al. The value of IL-6, PCT, qSOFA, NEWS, and SIRS to predict septic shock after Percutaneous nephrolithotomy. \u003cem\u003eBMC Urol\u003c/em\u003e. 2024;24(1):116.\u003c/li\u003e\n\u003cli\u003eZeng QB, Peng EL, Zhou Y, et al. Explainable machine learning model for predicting septic shock in critically sepsis patients based on coagulation indexes: A multicenter cohort study. \u003cem\u003eChin J Traumatol\u003c/em\u003e. S1008-1275(25)00032-X\u003c/li\u003e\n\u003cli\u003eOh MY, Kim HS, Jung YM, Lee HC, Lee SB, Lee SM. Machine Learning-Based Explainable Automated Nonlinear Computation Scoring System for Health Score and an Application for Prediction of Perioperative Stroke: Retrospective Study. \u003cem\u003eJ Med Internet Res\u003c/em\u003e. 2025;27:e58021.\u003c/li\u003e\n\u003cli\u003eRemeseiro B, Bolon-Canedo V. A review of feature selection methods in medical applications. \u003cem\u003eComput Biol Med\u003c/em\u003e. 2019;112:103375.\u003c/li\u003e\n\u003cli\u003eButala NM, Strom JB, Faridi KF, et al. Validation of Administrative Claims to Ascertain Outcomes in Pivotal Trials of Transcatheter Aortic Valve Replacement. \u003cem\u003eJACC Cardiovasc Interv\u003c/em\u003e. 2020;13(15):1777-1785.\u003c/li\u003e\n\u003cli\u003eHuang Y, Li W, Macheret F, Gabriel RA, Ohno-Machado L. A tutorial on calibration measurements and calibration models for clinical prediction models. \u003cem\u003eJ Am Med Inform Assoc\u003c/em\u003e. 2020;27(4):621-633.\u003c/li\u003e\n\u003cli\u003eNetto Flores Cruz G, Korthauer K. Bayesian Decision Curve Analysis With Bayesdca. \u003cem\u003eStat Med\u003c/em\u003e\u003cem\u003e.\u003c/em\u003e 43,30 (2024): 6042-6058.\u003c/li\u003e\n\u003cli\u003eVickers AJ, Van Calster B, Steyerberg EW. Net benefit approaches to the evaluation of prediction models, molecular markers, and diagnostic tests. \u003cem\u003eBMJ\u003c/em\u003e. 2016;352:i6.\u003c/li\u003e\n\u003cli\u003eda Cruz HF, Pfahringer B, Martensen T, et al. Using interpretability approaches to update \u0026quot;black-box\u0026quot; clinical prediction models: an external validation study in nephrology. \u003cem\u003eArtif Intell Med\u003c/em\u003e. 2021;111:101982.\u003c/li\u003e\n\u003cli\u003eHu J, Xu J, Li M, et al. Identification and validation of an explainable prediction model of acute kidney injury with prognostic implications in critically ill children: a prospective multicenter cohort study. \u003cem\u003eEClinicalMedicine\u003c/em\u003e. 2024;68:102409.\u003c/li\u003e\n\u003cli\u003eBerman R, Lee J, Balasubramanian A, Shah O. The Association of Perioperative Glycated Hemoglobin (Hemoglobin A1C) and the Risk of Sepsis after Ureteroscopy with Laser Lithotripsy. \u003cem\u003eJ Endourol\u003c/em\u003e. 2025;39(6):549-555.\u003c/li\u003e\n\u003cli\u003eWang L, Yu X, Qiu Z, et al. Influence of preoperative urine culture and bacterial species on urogenital sepsis after ureteral flexible lithotripsy in patients with upper urinary tract stones. \u003cem\u003eFront Med (Lausanne)\u003c/em\u003e. 2024;11:1393734.\u003c/li\u003e\n\u003cli\u003eLi Z, Fu C, Sun C, Suo Y, Li K, Qi S. Analysis of metabolic syndrome in bilateral upper urinary tract stones: A retrospective study of 3905 cases. \u003cem\u003eHeliyon\u003c/em\u003e. 2024;10(10):e31180.\u003c/li\u003e\n\u003cli\u003eCao Y, Cao H. Pathogen distribution and risk factors of positive stone culture for patients with upper urinary tract stone. \u003cem\u003eAm J Transl Res\u003c/em\u003e. 2025;17(5):3658-3664.\u003c/li\u003e\n\u003cli\u003eWang R, Dai W, Gong J, et al. Development of a novel combined nomogram model integrating deep learning-pathomics, radiomics and immunoscore to predict postoperative outcome of colorectal cancer lung metastasis patients. \u003cem\u003eJ Hematol Oncol\u003c/em\u003e. 2022;15(1):11.\u003c/li\u003e\n\u003cli\u003eHuang Y, Wang X, Cao Y, et al. Nomogram for Predicting Neoadjuvant Chemotherapy Response in Breast Cancer Using MRI-based Intratumoral Heterogeneity Quantification. \u003cem\u003eRadiology\u003c/em\u003e. 315,1 (2025): e241805.\u003c/li\u003e\n\u003cli\u003eGandaglia G, Ploussard G, Valerio M, et al. A Novel Nomogram to Identify Candidates for Extended Pelvic Lymph Node Dissection Among Patients with Clinically Localized Prostate Cancer Diagnosed with Magnetic Resonance Imaging-targeted and Systematic Biopsies. \u003cem\u003eEur Urol\u003c/em\u003e. 2019;75(3):506-514.\u003c/li\u003e\n\u003cli\u003eYang M, Li Y, Huang F. A nomogram for predicting postoperative urosepsis following retrograde intrarenal surgery in upper urinary calculi patients with negative preoperative urine culture. \u003cem\u003eSci Rep\u003c/em\u003e. 2023;13(1):2123.\u003c/li\u003e\n\u003cli\u003eXie W, Wu L, Yang M, Luo H, Li W, Li H. Association of preoperative electrocardiographic markers with sepsis in elderly patients after general surgery. \u003cem\u003eBMC Cardiovasc Disord\u003c/em\u003e. 2023;23(1):485.\u003c/li\u003e\n\u003cli\u003eShrestha N, Zorn-Pauly K, Mesirca P, et al. Lipopolysaccharide-induced sepsis impairs M2R-GIRK signaling in the mouse sinoatrial node. \u003cem\u003eProc Natl Acad Sci U S A\u003c/em\u003e. 2023;120(28):e2210152120.\u003c/li\u003e\n\u003cli\u003eJiaping W, Tingting H, Ming H, et al. Application of peripheral blood monocyte distribution width in the diagnosis of urosepsis. \u003cem\u003eDiagn Microbiol Infect Dis\u003c/em\u003e. 2025;113(1):116889.\u003c/li\u003e\n\u003cli\u003eLiu S, Wang X, She F, Zhang W, Liu H, Zhao X. Effects of Neutrophil-to-Lymphocyte Ratio Combined With Interleukin-6 in Predicting 28-Day Mortality in Patients With Sepsis. \u003cem\u003eFront Immunol\u003c/em\u003e. 2021;12:639735.\u003c/li\u003e\n\u003cli\u003eWu Y, Wang G, Huang Z, et al. Diagnostic and therapeutic value of biomarkers in urosepsis. \u003cem\u003eTher Adv Urol\u003c/em\u003e. 2023;15:17562872231151852.\u003c/li\u003e\n\u003cli\u003ePeng X, Jing X, Li T, Cheng J. Serum of interleukin-6 and procalcitonin as early diagnostic markers for the identification of poor hematopoietic reconstitution following allogeneic hematopoietic stem cell transplantation. \u003cem\u003eCancer\u003c/em\u003e. 2025;131(7):e35835.\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-informatics-and-decision-making","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"midm","sideBox":"Learn more about [BMC Medical Informatics and Decision Making](http://bmcmedinformdecismak.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/midm/default.aspx","title":"BMC Medical Informatics and Decision Making","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Diabetes, upper urinary tract stones, urosepsis, machine learning, risk prediction model","lastPublishedDoi":"10.21203/rs.3.rs-7584146/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7584146/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eObjective\u003c/h2\u003e\u003cp\u003eDiabetic patients are more prone to urinary tract infections due to metabolic abnormalities and impaired immune function, which can progress to urosepsis. This study aims to construct and validate an efficient and accurate predictive model, based on multimodal clinical data combined with machine learning techniques, to early assess the risk of postoperative infectious urosepsis in diabetic patients with urinary stones, thereby providing support for clinical decision-making.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e\u003cp\u003e532 patients diagnosed with diabetes who underwent surgical treatment for upper urinary tract stones was included. The patients were randomly divided into training (70%) and validation (30%) cohorts. A total of 164 multimodal clinical parameters were included, and those with statistically significant differences (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05) were selected. Feature selection was performed using LASSO regression and the Boruta algorithm. Nine machine learning (ML) algorithms were explored to predict the risk of postoperative infectious urosepsis in diabetic patients with urinary stones. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), learning curve, calibration curve, and decision curve analysis (DCA). The contribution of key predictive factors was visualized using the SHAP method.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e\u003cp\u003eAmong the 164 multimodal clinical parameters, 59 were significantly associated with the occurrence of postoperative infectious urosepsis. After feature selection, four key parameters were identified: p_IL_6, p_PCTp_ALB, p_T, and p_HR. Among the nine ML algorithms, logistic regression exhibited the best predictive ability. The AUC in the validation cohort was 0.903. The learning curve indicated good and stable model fitting, while the calibration curve demonstrated a high degree of agreement between predicted and actual probabilities. The decision curve analysis revealed that the model provided significant clinical net benefit within a threshold range of 5% to 90%.\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e\u003cp\u003eThe model constructed using logistic regression performed excellently in predicting the risk of postoperative infectious urosepsis in diabetic patients with urinary stones and can help clinicians better identify high-risk patients. Further prospective validation in multicenter studies is needed to confirm the model's generalizability.\u003c/p\u003e","manuscriptTitle":"Predicting Postoperative Sepsis Risk in Diabetic Urolithiasis Patients: A Multimodal Clinical Data-Driven Machine Learning Model","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-24 18:07:38","doi":"10.21203/rs.3.rs-7584146/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-02T11:48:51+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-01T09:24:13+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"336695499933145540640118640182499651631","date":"2026-03-31T14:20:41+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-19T22:33:37+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"336400298782004081793831811000204607840","date":"2025-11-11T14:59:06+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-10-10T09:25:38+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-17T04:43:14+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-17T04:43:09+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Medical Informatics and Decision Making","date":"2025-09-10T14:48:46+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-informatics-and-decision-making","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"midm","sideBox":"Learn more about [BMC Medical Informatics and Decision Making](http://bmcmedinformdecismak.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/midm/default.aspx","title":"BMC Medical Informatics and Decision Making","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"41f5d306-8829-4bf8-9d19-572e91b7108b","owner":[],"postedDate":"October 24th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2026-04-02T11:57:14+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-24 18:07:38","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7584146","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7584146","identity":"rs-7584146","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}