A Machine Learning-Based Model for Predicting Rhabdomyolysis in Patients With Sepsis

A Machine Learning-Based Model for Predicting Rhabdomyolysis in Patients With Sepsis | 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 A Machine Learning-Based Model for Predicting Rhabdomyolysis in Patients With Sepsis Xiangyi Zhou, Hongbin Deng, Daqian Gu, Fachun Zhou This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7904814/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 10 You are reading this latest preprint version Abstract Background Sepsis is a common condition in the intensive care unit (ICU) and is frequently complicated by rhabdomyolysis, which can lead to serious consequences such as acute kidney injury. Currently, there is a lack of effective tools for the early prediction of sepsis-associated rhabdomyolysis. Methods This retrospective study analyzed 3,782 sepsis patients from the MIMIC-IV database. Three feature selection methods (multivariate analysis, LASSO regression, and the Boruta algorithm) were used to identify predictors. Six machine learning models (logistic regression, decision tree, random forest, XGBoost, support vector machine, and artificial neural network) were developed to predict the occurrence of rhabdomyolysis. Results Ten predictive features were ultimately identified. The XGBoost model demonstrated the best performance, achieving an area under the receiver operating characteristic curve (AUC) of 0.924 (95% CI: 0.907–0.941) in the validation set. SHAP analysis revealed that the CK/CKMB ratio, aspartate aminotransferase (AST), and invasive mechanical ventilation were the most important predictors. Conclusions The machine learning-based prediction model accurately identifies the risk of rhabdomyolysis in sepsis patients, facilitating the early recognition of high-risk individuals and enabling timely interventions. Sepsis Rhabdomyolysis Machine Learning Predictive Model Intensive Care Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 22 Figure 23 Figure 24 Introduction Sepsis remains a major cause of morbidity and mortality in the intensive care unit (ICU), characterized by dysregulated host response and multiple organ dysfunction 1 . Beyond its well-recognized complications, sepsis has been increasingly associated with skeletal muscle injury, particularly rhabdomyolysis 2 , 3 . Rhabdomyolysis is defined as the breakdown of skeletal muscle fibers with subsequent release of intracellular components such as creatine kinase, myoglobin, and electrolytes into the circulation, leading to severe metabolic disturbances, acute kidney injury, and worsened clinical outcomes 2 , 4 . Previous reports suggest that systemic inflammation, tissue hypoperfusion, mitochondrial dysfunction, and exposure to myo-/nephrotoxic agents may synergistically contribute to rhabdomyolysis in septic patients 2 , 5 – 7 . Despite its clinical significance, rhabdomyolysis in the context of critical illness is often challenging to recognize early because classic symptoms are nonspecific and creatine kinase elevation is typically detected after muscle injury has occurred 2 , 4 . Early identification of septic patients at risk of rhabdomyolysis is of critical importance for timely interventions, including optimized hemodynamic resuscitation, avoidance of myotoxic drugs, and early renal protection strategies 2 , 4 . Conventional diagnostic approaches rely mainly on elevated creatine kinase levels after muscle damage has occurred, which limits the potential for early preventive measures. Furthermore, rhabdomyolysis may develop insidiously in critically ill patients, making clinical suspicion and diagnosis challenging 4 . Therefore, a reliable predictive model could help clinicians stratify risk, monitor high-risk patients more closely, and implement targeted preventive strategies before irreversible muscle injury and secondary organ damage occur. In recent years, machine learning techniques have shown great promise in healthcare by enabling the integration of large-scale, high-dimensional clinical data to generate accurate predictions and personalized risk assessments. Unlike traditional regression-based models, machine learning algorithms can capture complex nonlinear relationships and interactions among diverse clinical and laboratory variables, which are often present in sepsis pathophysiology 8 – 10 . Several machine learning-based models have already demonstrated superior performance in predicting complications such as acute kidney injury, septic shock, and mortality 8 – 13 . However, no predictive models specifically targeting sepsis-associated rhabdomyolysis have been systematically developed and validated to date. In this study, we aimed to construct and validate a machine learning-based predictive model for rhabdomyolysis in patients with sepsis using a large critical care database to provide clinicians with a practical tool for early risk stratification, thereby improving prevention and management strategies for this potentially life-threatening complication. Methods Data source and study population This retrospective cohort study was conducted using data from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database, a large, publicly available critical care database that contains detailed clinical information for patients admitted to the Beth Israel Deaconess Medical Center between 2008 and 2019. Access to the database was granted after completion of the required Collaborative Institutional Training Initiative course. Adult patients (≥ 18 years) with an ICU stay longer than 24 hours were eligible. Sepsis was defined according to Sepsis-3 criteria, requiring suspected infection combined with a Sequential Organ Failure Assessment (SOFA) score ≥ 2. Exclusion criteria included: (1) history of acute myocardial infarction, congestive heart failure, advanced chronic kidney disease, chronic renal failure, chronic liver failure, dermatomyositis, or polymyositis; (2) absence of creatine kinase (CK) measurements; and (3) CK > 1000 U/L prior to sepsis diagnosis. For patients with multiple ICU admissions, only the first ICU stay was analyzed. The patient selection process is summarized in Fig. 1 . Outcome definition The primary outcome was sepsis-associated rhabdomyolysis (RM), defined as serum CK level exceeding 1000 U/L after the onset of sepsis. Patients were classified into RM and non-RM groups accordingly. Feature extraction and preprocessing Demographic characteristics, comorbidities, vital signs, laboratory tests, severity scores (SOFA, SAPS II, APS III, OASIS, MELD, LODS, SIRS, GCS, Charlson Comorbidity Index), and treatment interventions (mechanical ventilation, cardiopulmonary resuscitation, continuous renal replacement therapy, renal replacement therapy) were extracted within the first 24 hours of ICU admission. Continuous variables were presented as medians with interquartile ranges, while categorical variables were presented as counts and percentages. Missing data were handled using multiple imputation with chained equations. Feature selection Three complementary methods were applied to identify robust predictors of RM: (1) multivariate logistic regression, selecting variables with p < 0.05; (2) least absolute shrinkage and selection operator (LASSO) regression with 10-fold cross-validation to minimize misclassification error; and (3) Boruta algorithm based on random forest importance scores. Features consistently identified by all three methods were considered final candidate predictors. Model development and validation The study cohort was randomly split into training (70%) and validation (30%) sets. Six machine learning algorithms were developed for RM prediction: logistic regression, decision tree, random forest, extreme gradient boosting (XGBoost), support vector machine (SVM), and artificial neural network (ANN). Hyperparameters were optimized through grid search with 5-fold cross-validation within the training set. Model evaluation Model performance was evaluated in the validation set using multiple metrics: area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, precision, F1 score, kappa statistic, Youden’s index, and positive and negative predictive values. Calibration curves with Brier scores and 95% confidence intervals were used to assess model calibration. Clinical utility was evaluated using decision curve analysis (DCA) (Fig. 3 ). Model interpretation To enhance interpretability, Shapley Additive Explanations (SHAP) analysis will be conducted on the model with the best performance. Global interpretability was assessed through mean absolute SHAP values and beeswarm plots, ranking the contribution of each predictor. Local interpretability was explored using waterfall plots to visualize the impact of individual features on the prediction for representative patients (Fig. 4 ). Statistical analysis Continuous variables were compared between groups using the Mann-Whitney U test, while categorical variables were compared using the chi-square or Fisher’s exact test, as appropriate. All statistical analyses were performed using R (version 4.2.0) and Python (version 3.9). A two-sided p value < 0.05 was considered statistically significant. Results Patient selection A total of 94,458 ICU admissions from the MIMIC-IV database were initially screened. After restricting to adult patients (≥ 18 years), with an ICU stay longer than 1 day, and fulfilling the Sepsis-3 criteria, 33,042 patients were eligible for further assessment. Patients with acute myocardial infarction (AMI), congestive heart failure (CHF), advanced chronic kidney disease (CKD stages 4–5), chronic renal failure (CRF), chronic liver failure (CLF), dermatomyositis (DM), or polymyositis (PM) were excluded. Subsequently, patients without peak CK measurements or with CK > 1000 U/L prior to the diagnosis of sepsis were also excluded. Finally, 3,782 patients were included in the analysis. The study cohort was randomly divided into a training set (70%) and an internal validation set (30%). Baseline characteristics A total of 3782 septic patients were included in the MIMIC-IV cohort, comprising 909 patients with rhabdomyolysis (RM group) and 2873 without rhabdomyolysis (non-RM group). Significant differences in demographic, clinical, and laboratory characteristics were observed between the two groups ( Table 1 ) . Table 1 Baseline characteristics and comparison between RM and non-RM in MIMIC database Demographic characteristics Overall n = 3782 Non-RM n = 2873 RM n = 909 P value Demographic information Male gender, n (%) 2148 [56.80] 1504 [52.35] 644 [70.85] < 0.001 Age(yd) 65.00 [55.00, 75.00] 67.00 [57.00, 76.00] 58.00 [49.00, 69.00] < 0.001 Height (cm) 170.00 [163.00, 178.00] 168.00 [163.00, 175.00] 173.00 [165.00, 178.00] < 0.001 Weight (kg) 79.00 [67.00, 94.50] 77.20 [65.50, 92.30] 84.60 [71.90, 98.60] < 0.001 BMI (kg/m 2 ) 27.47 [23.73, 32.03] 27.21 [23.44, 31.74] 28.41 [24.93, 32.86] < 0.001 Los_hospital (d) 16.76 [9.60, 27.80] 17.96 [10.04, 29.28] 13.61 [7.56, 22.71] < 0.001 Los_icu (d) 4.91 [2.44, 10.23] 4.67 [2.28, 9.84] 5.99 [2.84, 11.70] < 0.001 Severity of illness AKI_score (median [IQR]) 2.00 [2.00, 3.00] 2.00 [2.00, 3.00] 2.00 [2.00, 3.00] 0.005 Apsiii (median [IQR]) 54.00 [42.00, 67.00] 54.00 [43.00, 67.00] 53.00 [40.00, 69.00] 0.542 SAPSii (median [IQR]) 41.00 [33.00, 50.00] 41.00 [33.00, 49.00] 40.00 [31.00, 51.00] 0.266 SOFA (median [IQR]) 7.00 [5.00, 11.00] 7.00 [5.00, 10.00] 8.00 [6.00, 12.00] < 0.001 GCS (median [IQR]) 13.00 [9.00, 14.00] 13.00 [10.00, 14.00] 13.00 [9.00, 14.00] 0.002 SIRS (median [IQR]) 3.00 [2.00, 4.00] 3.00 [2.00, 3.00] 3.00 [3.00, 4.00] < 0.001 LODS (median [IQR]) 6.00 [4.00, 8.00] 6.00 [4.00, 8.00] 6.00 [4.00, 8.00] < 0.001 Charlson (median [IQR]) 5.00 [3.00, 7.00] 6.00 [4.00, 7.00] 3.00 [1.00, 6.00] < 0.001 MELD (median [IQR]) 17.58 [10.00, 24.68] 18.00 [11.00, 25.00] 16.57 [10.00, 24.00] 0.038 OASIS (median [IQR]) 35.00 [30.00, 40.00] 35.00 [29.00, 40.00] 36.00 [31.00, 42.00] < 0.001 Vital signs < 0.001 Temperature (℃) 37.39 [37.00, 37.94] 37.28 [37.00, 37.83] 37.70 [37.20, 38.28] 0.002 HR (bpm) 109.00 [96.00, 122.00] 108.00 [96.00, 121.00] 111.00 [98.00, 122.00] 0.045 RR (bpm) 28.75 [25.00, 33.00] 29.00 [25.00, 33.00] 28.00 [24.00, 32.00] < 0.001 SBP (mmHg) 144.00 [130.00, 158.00] 143.00 [129.00, 157.00] 146.00 [134.00, 162.00] < 0.001 DBP (mmHg) 84.00 [73.00, 96.00] 84.00 [73.00, 96.00] 85.00 [76.00, 97.00] < 0.001 MBP (mmHg) 99.75 [89.00, 112.00] 99.00 [88.00, 111.00] 103.00 [93.00, 116.00] 0.542 Laboratory fndings Spo2 (%) 100.00 [100.00, 100.00] 100.00 [100.00, 100.00] 100.00 [100.00, 100.00] 0.037 Calcium_free (mmol/L) 1.13 [1.08, 1.19] 1.13 [1.08, 1.19] 1.14 [1.08, 1.20] 0.007 WBC (K/uL) 12.70 [8.70, 17.80] 12.30 [8.30, 17.60] 13.50 [10.00, 18.40] < 0.001 Hematocrit % 31.80 [28.20, 36.00] 30.90 [27.70, 34.80] 34.60 [31.10, 38.60] < 0.001 MCH (pg) 30.50 [28.90, 31.90] 30.40 [28.70, 31.80] 30.70 [29.40, 32.00] < 0.001 MCV (fL) 93.00 [88.00, 97.00] 93.00 [88.00, 98.00] 92.00 [88.00, 96.00] 0.005 MCHC (%) 33.20 [32.00, 34.30] 32.90 [31.90, 34.10] 33.90 [32.70, 34.90] < 0.001 RDW (%) 15.60 [14.30, 17.10] 16.00 [14.60, 17.50] 14.70 [13.70, 15.60] < 0.001 PLT (K/uL) 189.00 [125.00, 258.00] 190.00 [121.00, 261.00] 188.00 [139.00, 248.00] 0.451 RBC (m/uL) 3.48 [3.05, 3.98] 3.37 [2.97, 3.85] 3.80 [3.39, 4.26] < 0.001 Alb (g/dl) 2.90 [2.60, 3.30] 2.90 [2.50, 3.30] 3.10 [2.70, 3.40] < 0.001 Creatinine (mg/dl) 1.30 [0.90, 2.30] 1.30 [0.80, 2.20] 1.50 [1.00, 2.40] < 0.001 BUN (mg/dl) 28.00 [17.00, 43.00] 29.00 [18.00, 45.00] 25.00 [16.00, 38.00] < 0.001 Aniongap 16.00 [13.00, 19.00] 16.00 [13.00, 18.00] 17.00 [14.00, 20.00] < 0.001 PT (seconds) 15.30 [13.30, 19.10] 15.50 [13.30, 19.50] 14.90 [13.00, 17.90] < 0.001 PTT (seconds) 33.50 [28.70, 42.48] 33.70 [28.90, 42.30] 32.70 [28.30, 42.90] 0.139 INR 1.40 [1.20, 1.80] 1.40 [1.20, 1.80] 1.30 [1.20, 1.70] < 0.001 CK_CKMB_ratio (U/L) 33.00 [14.00, 92.00] 23.00 [11.00, 54.00] 111.00 [57.00, 210.00] < 0.001 ALT (U/L) 33.00 [18.00, 75.75] 29.00 [16.00, 60.00] 58.00 [29.00, 161.00] < 0.001 AST (U/L) 50.00 [27.00, 120.00] 40.00 [24.00, 84.00] 117.00 [54.00, 335.00] < 0.001 ALP (U/L) 88.00 [62.00, 133.00] 95.00 [67.00, 142.00] 66.00 [49.00, 95.00] < 0.001 Bilirubin_total (mg/dl) 0.80 [0.40, 1.70] 0.80 [0.40, 1.80] 0.70 [0.40, 1.40] < 0.001 LDH (U/L) 308.00 [218.00, 477.00] 277.00 [205.00, 408.00] 453.00 [302.00, 702.00] < 0.001 Chloride (mg/dl) 106.00 [102.00, 110.00] 105.00 [101.00, 110.00] 108.00 [104.00, 112.00] < 0.001 Glucose (mg/dl) 155.50 [121.00, 204.00] 150.00 [119.00, 198.00] 171.00 [132.00, 224.00] < 0.001 Bicarbonate (g/dl) 24.00 [21.00, 26.00] 24.00 [21.00, 27.00] 23.00 [21.00, 26.00] < 0.001 Hb (g/dl) 10.50 [9.20, 11.90] 10.10 [8.90, 11.40] 11.70 [10.40, 12.90] < 0.001 K (mEq/L) 4.40 [4.00, 4.90] 4.30 [4.00, 4.80] 4.60 [4.10, 5.20] < 0.001 Na (mEq/L) 140.00 [137.00, 143.00] 139.00 [136.00, 142.00] 141.00 [138.00, 144.00] < 0.001 Mg (mg/dL) 2.20 [1.90, 2.40] 2.20 [1.90, 2.40] 2.20 [2.00, 2.50] < 0.001 Ca(mg/dL) 8.40 [7.90, 8.80] 8.40 [7.90, 8.90] 8.30 [7.90, 8.70] < 0.001 P (mg/dL) 4.10 [3.30, 5.10] 4.00 [3.20, 4.90] 4.40 [3.50, 5.40] < 0.001 Input_24h_sum (ml) 4964.50 [2649.00, 8077.00] 4255.00 [2301.00, 7067.00] 7327.00 [4617.00, 10827.00] < 0.001 Output_24h_sum (ml) 1860.00 [1050.00, 3033.75] 1770.00 [994.00, 2810.00] 2340.00 [1306.50, 3580.00] < 0.001 Output_urine_sum (ml) 1302.50 [743.50, 2050.00] 1270.00 [729.00, 1975.00] 1430.00 [830.00, 2240.00] < 0.001 Comorbidity, n (%) Smoker (%) 328 ( 8.67) 252 ( 8.77) 76 ( 8.36) 0.752 Alcohol_abuse (%) 59 ( 1.56) 41 ( 1.43) 18 ( 1.98) 0.308 Hypertension (%) 1391 (36.78) 1046 (36.41) 345 (37.95) 0.422 Diabetes (%) 1204 (31.84) 978 (34.04) 226 (24.86) < 0.001 Myocardial_infarct (%) 279 ( 7.38) 224 ( 7.80) 55 ( 6.05) 0.092 Congestive_heart_failure (%) 1230 (32.52) 1026 (35.71) 204 (22.44) < 0.001 Mild_liver_disease (%) 890 (23.53) 697 (24.26) 193 (21.23) 0.067 Severe_liver_disease (%) 472 (12.48) 426 (14.83) 46 ( 5.06) < 0.001 Renal_disease (%) 1016 (26.86) 856 (29.79) 160 (17.60) < 0.001 Chronic_pulmonary_disease (%) 1059 (28.00) 836 (29.10) 223 (24.53) 0.009 Cerebrovascular_disease (%) 550 (14.54) 405 (14.10) 145 (15.95) 0.184 Peripheral_vascular_disease (%) 504 (13.33) 373 (12.98) 131 (14.41) 0.294 Dementia (%) 123 ( 3.25) 105 ( 3.65) 18 ( 1.98) 0.018 Peptic_ulcer_disease (%) 162 ( 4.28) 140 ( 4.87) 22 ( 2.42) 0.002 Paraplegia (%) 197 ( 5.21) 146 ( 5.08) 51 ( 5.61) 0.589 Malignant_cancer (%) 578 (15.28) 509 (17.72) 69 ( 7.59) < 0.001 Metastatic_solid_tumor (%) 179 ( 4.73) 151 ( 5.26) 28 ( 3.08) 0.009 Aids (%) 41 ( 1.08) 30 ( 1.04) 11 ( 1.21) 0.812 Rheumatic_disease (%) 171 ( 4.52) 144 ( 5.01) 27 ( 2.97) 0.013 AKI (%) 3224 (85.25) 2422 (84.30) 802 (88.23) 0.004 Treatment status InvasiveVent (%) 2348 (62.08) 1588 (55.27) 760 (83.61) < 0.001 CPR (%) 76 ( 2.01) 45 ( 1.57) 31 ( 3.41) 0.001 CRRT (%) 555 (14.67) 363 (12.63) 192 (21.12) < 0.001 RRT (%) 772 (20.41) 544 (18.93) 228 (25.08) < 0.001 Data are shown as median with interquartile range (IQR) for continuous variables and number with percentage for categorical variables SOFA: Sequential Organ Failure Assessment, SAPSII: Simplified Acute Physiology Score II, APSIII: Acute Physiology Score III, OASIS: Oxford Acute Severity of Illness Score, GCS: Glasgow Coma Scale, SIRS: Systemic Inflammatory Response Syndrome, LODS: Logistic Organ Dysfunction System, MELD: Model for End-Stage Liver Disease, Charlson: Charlson Comorbidity Index, RM: Rhabdomyolysis, BMI: Body Mass Index, HR: Heart Rate, RR: Respiratory Rate, SBP: Systolic Blood Pressure, DBP: Diastolic Blood Pressure, MBP: Mean Blood Pressure, SpO2: Oxygen Saturation, WBC: White Blood Cell, MCH: Mean Corpuscular Hemoglobin, MCV: Mean Corpuscular Volume, MCHC: Mean Corpuscular Hemoglobin Concentration, RDW: Red Cell Distribution Width, PLT: Platelet, RBC: Red Blood Cell, Alb: Albumin, BUN: Blood Urea Nitrogen, PT: Prothrombin Time, PTT: Partial Thromboplastin Time, INR: International Normalized Ratio, ALT: Alanine Aminotransferase, AST: Aspartate Aminotransferase, ALP: Alkaline Phosphatase, LDH: Lactate Dehydrogenase, Hb: Hemoglobin, AKI: Acute Kidney Injury, CPR: Cardiopulmonary Resuscitation, CRRT: Continuous Renal Replacement Therapy, RRT: Renal Replacement Therapy, IQR: Interquartile Range Patients in the RM group were younger, more frequently male, and had higher body weight and body mass index compared with the non-RM group (all p < 0.001). Although hospital length of stay was shorter in the RM group, ICU length of stay was significantly longer (both p < 0.001). Regarding disease severity, RM patients had higher SOFA, SIRS, LODS, and OASIS scores, while Charlson Comorbidity Index was lower (p < 0.001). RM patients presented with higher temperature, heart rate, and blood pressure levels. Laboratory findings revealed substantial differences between groups. The RM group showed significantly higher white blood cell counts, hematocrit, creatinine, anion gap, liver enzymes (ALT, AST), LDH, glucose, potassium, and phosphorus levels, whereas platelet counts and bilirubin were lower. CK/CKMB ratio was markedly elevated in the RM group (111.00 [57.00–210.00] vs. 23.00 [11.00–54.00], p < 0.001). Compared with the non-RM group, RM patients had lower prevalence of diabetes, congestive heart failure, severe liver disease, and renal disease, but higher prevalence of acute kidney injury (88.23% vs. 84.30%, p = 0.004). In terms of treatment, invasive mechanical ventilation (InvasiveVent), cardiopulmonary resuscitation (CPR), continuous renal replacement therapy (CRRT), and renal replacement therapy (RRT) were all more frequently used in the RM group (all p < 0.001). Feature selection To identify robust predictors of sepsis-associated rhabdomyolysis, three complementary feature selection methods were applied: multivariate analysis, LASSO regression, and the Boruta algorithm ( Fig. 2 ) . In the LASSO regression with 10-fold cross-validation, the misclassification error across different values of the tuning parameter was evaluated. The two vertical dashed lines indicate the optimal lambda values under the minimum and 1-standard error (SE) criteria, respectively. Using this approach, a total of 33 variables with non-zero coefficients were retained ( Fig. 2 A-B ) . The Boruta algorithm further ranked variable importance by comparing each feature with shadow features. Among all candidates, 22 variables were identified as important, while others were classified as neutral or rejected ( Fig. 2 C-D ) . The intersection of the three approaches yielded 10 overlapping predictors that were consistently associated with rhabdomyolysis, common variables are provided in the supplementary file. These variables were selected as the final candidate predictors for subsequent model construction ( Fig. 2 E ) . Model performance in the validation set The predictive performance of six machine learning models-including logistic regression, decision tree, random forest, XGBoost, SVM, and ANN-was comprehensively evaluated in the validation set ( Fig. 3 ) . Calibration analysis demonstrated that all models exhibited acceptable agreement between predicted and observed probabilities, with XGBoost and random forest showing the closest alignment to the ideal reference line and the lowest Brier scores ( Fig. 3 A ) . DCA further revealed that machine learning models, particularly XGBoost and random forest, provided greater net clinical benefit across a wide range of threshold probabilities compared with the strategies of treating all or treating none ( Fig. 3 B ) . Receiver operating characteristic curves confirmed the superior discriminative performance of XGBoost, with the highest AUC, followed by random forest and ANN. Logistic regression and decision tree showed moderate discrimination, whereas SVM achieved good specificity but relatively lower sensitivity ( Fig. 3 C ) . The parameters of each model are provided in the supplementary file. Collectively, these results indicated that ensemble-based models, especially XGBoost, outperformed other approaches in predicting sepsis-associated rhabdomyolysis, The detailed performance metrics of all models in the validation set are presented in Table 2 . Table 2 Performance of 6 machine learning-based models for predicting ICU admission in the validation set Model AUC 95% CI Lower 95% CI Upper Accuracy Precision Sensitivity Specificity F1 Score Kappa Youden's J PPV NPV Logistic 0.877 0.856 0.898 0.826 0.712 0.463 0.941 0.561 0.459 0.404 0.712 0.847 Decision Tree 0.886 0.864 0.907 0.853 0.709 0.662 0.914 0.684 0.589 0.576 0.709 0.895 Random Forest 0.911 0.891 0.930 0.876 0.799 0.643 0.949 0.713 0.635 0.592 0.799 0.894 XGBoost 0.924 0.907 0.941 0.883 0.791 0.695 0.942 0.740 0.664 0.637 0.791 0.907 SVM 0.885 0.866 0.905 0.825 0.720 0.445 0.945 0.550 0.449 0.390 0.720 0.844 ANN 0.911 0.893 0.929 0.865 0.772 0.621 0.942 0.688 0.603 0.563 0.772 0.887 AUC: area under the receiver operating characteristic curve; XGBoost: eXtreme gradient boosting; SVM: Support Vector Machine; ANN: Artificial Neural Network Model interpretation with SHAP analysis To enhance the interpretability of the best-performing model, SHAP analysis was applied to the XGBoost model (Fig. 4 ). The bar plot of mean absolute SHAP values ranked the importance of each predictor, revealing that the CK/CKMB ratio, AST, and InvasiveVent were the top three contributors to model predictions ( Fig. 4 A ) . The beeswarm plot further demonstrated the distribution of SHAP values across individual patients, where higher values of CK/CKMB ratio, AST, and LDH were strongly associated with increased risk of rhabdomyolysis, while higher albumin and phosphorus levels contributed negatively to risk prediction ( Fig. 4 B ) . Individual-level explanations were provided through waterfall plots. For a representative RM patient, positive SHAP values from protective variables such as higher albumin offset the contributions from risk factors, shifting the prediction probability toward a low risk outcome (baseline expectation E[f(X)] = 0.758; model output f(x) = 0.957) ( Fig. 4 C ) . Conversely, for a representative non-RM patient, elevated CK/CKMB ratio, AST, and requirement of invasive ventilation exerted strong positive SHAP contributions, driving the model prediction toward high risk of rhabdomyolysis (baseline expectation E[f(X)] = 0.242; model output f(x) = 0.043) ( Fig. 4 D ) . These findings indicate that the XGBoost model not only achieves high predictive performance but also provides clinically interpretable insights into the relative contribution of key laboratory markers and treatment variables. Discussion RM is a life-threatening complication in ICU patients with sepsis, as it exacerbates systemic inflammation, induces acute kidney injury (AKI) via myoglobin-mediated tubular damage, and significantly increases hospital mortality 14 , 15 . In our study, AKI incidence was significantly higher in patients with RM than in non-RM patients, reflecting the bidirectional pathophysiological link between RM and AKI in sepsis. Mechanistically, myoglobin released during RM-induced skeletal muscle necrosis directly causes renal tubular obstruction, oxidative stress, and inflammation—effects that combined with sepsis-related renal ischemia, exacerbate kidney dysfunction 2 , 16 ; conversely, preexisting AKI impairs myoglobin and cytokine clearance, amplifying muscle necrosis and forming a vicious cycle 17 . Clinically, this comorbidity correlates with longer ICU stays (5.99 days in RM vs. 4.67 days in non-RM patients), highlighting the need for prioritized renal monitoring in RM patients. The RM group patients experienced more frequent invasive ventilation (83.61% vs. 55.27%) and CRRT (21.12% vs. 12.63%), indicating that RM might drive advanced organ support, showing the needs for integrated assessment of muscle injury and renal function in septic patients. Several studies have focused on predicting outcomes in patients with RM 18,19 , however, there are few studies investigating the prediction of the occurrence of rhabdomyolysis. Traditional RM prediction relies on single biomarkers (e.g., CK) with limited early sensitivity, and no tailored risk stratification tools exist for septic populations 20 . To address this gap, we developed an interpretable machine learning model for RM prediction in ICU septic patients, with the XGBoost model emerging as the optimal approach. This model achieved an AUC of 0.924 (95% CI: 0.907–0.941) and a Brier score of 0.90 in the testing set, outperforming logistic regression and other machine learning algorithms (e.g., random forest, ANN). DCA further confirmed its clinical utility, as it provided higher net benefits across a wide threshold probability range (0.1–0.8) compared to "treat all" or "treat none" strategies—critical for guiding targeted interventions and optimizing ICU resource allocation. The SHAP analysis identified CK-CKMB ratio, AST, and InvasiveVent as the top three predictors of RM-findings that supported by both pathophysiological mechanisms and existing literature. The CK-CKMB ratio stood out as the most influential predictor of RM. Notably, RM is clinically defined by an acute increase in serum CK to more than five times the upper normal limit, with myocardial infarction excluded based on a CK-MB fraction < 5% 21 . Aligning with this diagnostic framework, our data showed a 4.8-fold higher ratio in RM versus non-RM patients (111 vs. 23 U/L, P < 0.001), indicating that higher CK-CKMB ratio is associated with increased skeletal muscle injury. There is observational and experimental data demonstrating that AST can be elevated in patients with RM due to muscle release of these enzymes 22 , Liver failure was more common for intense RM patients 23 . In addition, sepsis could induce liver injury in any stage, and liver dysfunction is one of the hallmarks of the progressive development of sepsis into multi-organ dysfunction 24 . These studies could explain the elevation of AST in sepsis patients with RM. Notably, our study also found that elevated AST (117 vs. 40 U/L, P < 0.001) serve as indirect markers of skeletal muscle damage. However, whether there is an interaction between the liver and skeletal muscle during the development of rhabdomyolysis requires further basic research to confirm. Diaphragm biopsy specimens obtained from mechanically ventilated patients exhibit significant inflammatory infiltration and sarcomeric disarray—pathological features that closely resemble those observed in animal models of load-induced muscle injury 25 , 26 . Notably, high levels of respiratory effort are frequently documented in mechanically ventilated patients; this phenomenon is primarily driven by elevated respiratory drive, insufficient ventilator support, and episodes of patient–ventilator dyssynchrony. Collectively, these factors suggest that critically ill patients undergoing mechanical ventilation are at substantial risk of developing load-induced diaphragm injury 27 . Similarly, our study showed that the proportion of patients requiring InvasiveVent was significantly higher in the RM group than in the non-RM group. However, whether InvasiveVent directly contributes to RM via ventilator-induced diaphragm injury or disuse atrophy requires further basic and clinical research to be validated. Interestingly, SHAP analysis showed the negative contribution of InvasiveVent to RM prediction, indicating that InvasiveVent itself may confer indirect benefits via improved organ perfusion. This study advances existing knowledge in three key ways. First, it is the first to develop an machine learning-based RM prediction model specifically for ICU septic patients, whereas previous studies focused on narrow subgroups such as trauma and drug-induced RM 28,29 . Our large sample size (3782 patients from the MIMIC database) and multi-method feature selection (univariate analysis, Lasso, Boruta) enhance the model’s robustness and generalizability. Second, the emphasis on model interpretability via SHAP addresses a major limitation of "black-box" machine learning models in clinical practice: we not only identified key predictors but also quantified their individual contributions (e.g., a CK-CKMB ratio of 111 U/L increases RM probability by ~ 5%), facilitating clinician trust and adoption 30 . Third, the XGBoost model’s ability to capture non-linear interactions outperforms traditional linear models, which often fail to account for the complex crosstalk between inflammation and organ dysfunction in sepsis 31 . This study has several limitations. First, due to the lack of an independent external cohort, we only performed internal validation through training/testing set splitting. This may restrict the model’s generalizability to other ICU populations, such as those in European or Asian settings where sepsis management protocols differ 32 , 33 . Second, the retrospective design led to missing data on critical variables—including myoglobin levels (a direct marker of RM) and sepsis etiology, such as whether infections were bacterial or viral. The inclusion of these variables could have potentially improved the model’s predictive performance. Third, the model was developed solely based on baseline admission data and did not incorporate dynamic changes in biomarkers (e.g., serial creatine kinase measurements) or clinical interventions like fluid resuscitation. Such dynamic information is critical for real-time assessment of rhabdomyolysis risk in clinical practice. Finally, we were unable to establish a causal relationship between certain predictors (e.g., InvasiveVent) and RM. This is because InvasiveVent may reflect the severity of sepsis rather than act as a direct cause of muscle injury. In conclusion, we developed a highly performant and interpretable XGBoost model to predict RM in ICU septic patients, using readily available clinical variables (CK-CKMB ratio, AST, InvasiveVent) that facilitate seamless clinical implementation. Future studies should focus on external validation in multi-center prospective cohorts, integrating dynamic biomarkers (e.g., serial myoglobin) to develop real-time prediction tools, and conducting randomized controlled trials to verify whether model-guided interventions reduce RM-related AKI and mortality. With further refinement, this model has the potential to become a standard tool for early RM risk stratification in septic patients, improving clinical decision-making and patient outcomes. Abbreviations AKI Acute kidney injury AMI Acute myocardial infarction ANN Artificial neural network AUC Area under the receiver operating characteristic curve CHF Congestive heart failure CK Creatine kinase CKD Chronic kidney disease CLF Chronic liver failure CPR Cardiopulmonary resuscitation CRF Chronic renal failure CRRT Continuous renal replacement therapy ICU Intensive care unit DCA Decision curve analysis DM Dermatomyositis InvasiveVent Invasive mechanical ventilation LASSO Least absolute shrinkage and selection operator MIMIC-IV Intensive Care IV PM Polymyositis RM Rhabdomyolysis RRT Renal replacement therapy SE Standard error SHAP Shapley Additive Explanations SOFA Sequential Organ Failure Assessment SVM Support vector machine XGBoost Extreme gradient boosting Declarations Submission declaration and verification The work described has not been published previously, and is not under consideration for publication elsewhere. Ethics approval and consent to participate This retrospective study utilized data from the publicly available MIMIC-IV database. The requirement for ethical approval and informed consent was waived by the Institutional Review Board of Tianjin Medical University General Hospital. The study was conducted in accordance with the Declaration of Helsinki. Access to the MIMIC-IV database was granted after completing the required Collaborative Institutional Training Initiative (CITI) course. Consent for publication All the authors have consented to the publication of this research. Availability of data and materials The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request. Competing interests The authors declare that they have no competing interests. Funding This study was supported by the Science and Technology Commission of Chongqing (No.0202czzx2106), National Natural Science Foundation of China (No.82502660). Clinical trial number Not applicable. Author contributions statement Daqian Gu gave the study concept and design; Hongbin Deng drafted the manuscript; Xiangyi Zhou carried out the statistical analysis; Fachun Zhou supervised the study; all authors read and approved the final manuscript. Acknowledgments None. References Singer M, Deutschman CS, Seymour CW, et al. The Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3). JAMA. 2016;315(8):801–10. Torres PA, Helmstetter JA, Kaye AM, Kaye AD. Rhabdomyolysis: pathogenesis, diagnosis, and treatment. Ochsner J. 2015;15(1):58–69. Rawson ES, Clarkson PM, Tarnopolsky MA. Perspectives on exertional rhabdomyolysis. Sports Med. 2017;47(Suppl 1):33–49. Rout P, Chippa V, Adigun R. Rhabdomyolysis. StatPearls. Treasure Island (FL) ineligible companies. Disclosure: Venu Chippa declares no relevant financial relationships with ineligible companies. Disclosure: Rotimi Adigun declares no relevant financial relationships with ineligible companies.: StatPearls Publishing Copyright © 2025. StatPearls Publishing LLC.; 2025. Nedel W, Deutschendorf C, Portela LVC. Sepsis-induced mitochondrial dysfunction: A narrative review. World J Crit Care Med. 2023;12(3):139. Hu D, Sheeja Prabhakaran H, Zhang Y-Y, Luo G, He W, Liou Y-C. Mitochondrial dysfunction in sepsis: mechanisms and therapeutic perspectives. Crit Care. 2024;28(1):292. Sun J, Zhang J, Tian J, et al. Mitochondria in sepsis-induced AKI. J Am Soc Nephrol. 2019;30(7):1151–61. Tomašev N, Glorot X, Rae JW, et al. A clinically applicable approach to continuous prediction of future acute kidney injury. Nature. 2019;572(7767):116–9. Henry KE, Hager DN, Pronovost PJ, Saria S. A targeted real-time early warning score (TREWScore) for septic shock. Sci Transl Med. 2015;7(299):ra299122–299122. Goh KH, Wang L, Yeow AYK, et al. Artificial intelligence in sepsis early prediction and diagnosis using unstructured data in healthcare. Nat Commun. 2021;12(1):711. Desautels T, Calvert J, Hoffman J, et al. Prediction of sepsis in the intensive care unit with minimal electronic health record data: a machine learning approach. JMIR Med Inf. 2016;4(3):e5909. Hou N, Li M, He L, et al. Predicting 30-days mortality for MIMIC-III patients with sepsis-3: a machine learning approach using XGboost. J translational Med. 2020;18(1):462. Zhang Y, Xu W, Yang P, Zhang A. Machine learning for the prediction of sepsis-related death: a systematic review and meta-analysis. BMC Med Inf Decis Mak. 2023;23(1):283. Wang Z, Wang Q, Chen J, Cai L. Rhabdomyolysis in intensive care unit—distinctive clinical indicators and prognosis. BMC Anesthesiol. 2025;25(1):84. Miyauchi H, Okubo K, Iida K, et al. Multiple site inflammation and acute kidney injury in crush syndrome. Front Pharmacol. 2024;15:1458997. Bellomo R, Kellum JA, Ronco C, et al. Acute kidney injury in sepsis. Intensive Care Med. 2017;43(6):816–28. Zhou X, Yang Y, Li P, Wang F, Zhang L, Fu P. Efficacy of haemoadsorption combined with continuous renal replacement therapy in patients with rhabdomyolysis and acute kidney injury: a retrospective study. Clin kidney J. 2025;18(2):sfae406. Liu C, Liu X, Mao Z, et al. Interpretable machine learning model for early prediction of mortality in ICU patients with rhabdomyolysis. Med Sci Sports Exerc. 2021;53(9):1826–34. Liu C, Shi J, Wang F et al. Development and validation of an interpretable multi-task model to predict outcomes in patients with rhabdomyolysis: a multicenter retrospective cohort study. EClinicalMedicine 2025;87. Lippi G, Schena F, Ceriotti F. Diagnostic biomarkers of muscle injury and exertional rhabdomyolysis. Clin Chem Lab Med (CCLM). 2018;57(2):175–82. Lane R, Phillips M. Rhabdomyolysis. In. Vol 327: British Medical Journal Publishing Group; 2003:115–116. Lim AK. Abnormal liver function tests associated with severe rhabdomyolysis. World J Gastroenterol. 2020;26(10):1020. Martinez T, Liaud-Laval G, Laitselart P, et al. Study of the relationship between liver function markers and traumatic rhabdomyolysis: a retrospective study of hemorrhagic patients admitted to intensive care unit in a level I trauma center. Anesth Analgesia. 2023;136(5):842–51. Liu Z, Yuan X, Huang Y et al. The role of interferon-induced proteins with tetratricopeptide repeats 1 and 2 in Sepsis-induced acute liver injury. Infect Drug Resist 2024:2337–49. Van den Berg M, Hooijman PE, Beishuizen A, et al. Diaphragm atrophy and weakness in the absence of mitochondrial dysfunction in the critically ill. Am J Respir Crit Care Med. 2017;196(12):1544–58. Jaber S, Petrof BJ, Jung B, et al. Rapidly progressive diaphragmatic weakness and injury during mechanical ventilation in humans. Am J Respir Crit Care Med. 2011;183(3):364–71. Schreiber A, Bertoni M, Goligher EC. Avoiding respiratory and peripheral muscle injury during mechanical ventilation: diaphragm-protective ventilation and early mobilization. Crit Care Clin. 2018;34(3):357–81. Tarazona V, Figueiredo S, Hamada S, et al. Admission serum myoglobin and the development of acute kidney injury after major trauma. Ann Intensiv Care. 2021;11(1):140. Yamanaka T, Takemura K, Hayashida M, Suyama K, Urakami S, Miura Y. Cabozantinib-induced serum creatine kinase elevation and rhabdomyolysis: a retrospective case series. Cancer Chemother Pharmacol. 2023;92(3):235–40. Huang D, Gong L, Wei C, Wang X, Liang Z. An explainable machine learning-based model to predict intensive care unit admission among patients with community-acquired pneumonia and connective tissue disease. Respir Res. 2024;25(1):246. Li X, Wu R, Zhao W, et al. Machine learning algorithm to predict mortality in critically ill patients with sepsis-associated acute kidney injury. Sci Rep. 2023;13(1):5223. Gildea A, Mulvihill C, McFarlane E, Gray A, Singer M. Recognition, diagnosis, and early management of suspected sepsis: summary of updated NICE guidance. BMJ 2024;385. Mehta Y, Paul R, Rabbani R, Acharya SP, Withanaarachchi UK. Sepsis management in Southeast Asia: a review and clinical experience. J Clin Med. 2022;11(13):3635. Tables Table 1 Baseline characteristics and comparison between RM and non-RM in MIMIC database Demographic characteristics Overall n=3782 Non-RM n=2873 RM n=909 P value Demographic information Male gender, n (%) 2148 [56.80] 1504 [52.35] 644 [70.85] <0.001 Age(yd) 65.00 [55.00, 75.00] 67.00 [57.00, 76.00] 58.00 [49.00, 69.00] <0.001 Height (cm) 170.00 [163.00, 178.00] 168.00 [163.00, 175.00] 173.00 [165.00, 178.00] <0.001 Weight (kg) 79.00 [67.00, 94.50] 77.20 [65.50, 92.30] 84.60 [71.90, 98.60] <0.001 BMI (kg/m 2 ) 27.47 [23.73, 32.03] 27.21 [23.44, 31.74] 28.41 [24.93, 32.86] <0.001 Los_hospital (d) 16.76 [9.60, 27.80] 17.96 [10.04, 29.28] 13.61 [7.56, 22.71] <0.001 Los_icu (d) 4.91 [2.44, 10.23] 4.67 [2.28, 9.84] 5.99 [2.84, 11.70] <0.001 Severity of illness AKI_score (median [IQR]) 2.00 [2.00, 3.00] 2.00 [2.00, 3.00] 2.00 [2.00, 3.00] 0.005 Apsiii (median [IQR]) 54.00 [42.00, 67.00] 54.00 [43.00, 67.00] 53.00 [40.00, 69.00] 0.542 SAPSii (median [IQR]) 41.00 [33.00, 50.00] 41.00 [33.00, 49.00] 40.00 [31.00, 51.00] 0.266 SOFA (median [IQR]) 7.00 [5.00, 11.00] 7.00 [5.00, 10.00] 8.00 [6.00, 12.00] <0.001 GCS (median [IQR]) 13.00 [9.00, 14.00] 13.00 [10.00, 14.00] 13.00 [9.00, 14.00] 0.002 SIRS (median [IQR]) 3.00 [2.00, 4.00] 3.00 [2.00, 3.00] 3.00 [3.00, 4.00] <0.001 LODS (median [IQR]) 6.00 [4.00, 8.00] 6.00 [4.00, 8.00] 6.00 [4.00, 8.00] <0.001 Charlson (median [IQR]) 5.00 [3.00, 7.00] 6.00 [4.00, 7.00] 3.00 [1.00, 6.00] <0.001 MELD (median [IQR]) 17.58 [10.00, 24.68] 18.00 [11.00, 25.00] 16.57 [10.00, 24.00] 0.038 OASIS (median [IQR]) 35.00 [30.00, 40.00] 35.00 [29.00, 40.00] 36.00 [31.00, 42.00] <0.001 Vital signs <0.001 Temperature (℃) 37.39 [37.00, 37.94] 37.28 [37.00, 37.83] 37.70 [37.20, 38.28] 0.002 HR (bpm) 109.00 [96.00, 122.00] 108.00 [96.00, 121.00] 111.00 [98.00, 122.00] 0.045 RR (bpm) 28.75 [25.00, 33.00] 29.00 [25.00, 33.00] 28.00 [24.00, 32.00] <0.001 SBP (mmHg) 144.00 [130.00, 158.00] 143.00 [129.00, 157.00] 146.00 [134.00, 162.00] <0.001 DBP (mmHg) 84.00 [73.00, 96.00] 84.00 [73.00, 96.00] 85.00 [76.00, 97.00] <0.001 MBP (mmHg) 99.75 [89.00, 112.00] 99.00 [88.00, 111.00] 103.00 [93.00, 116.00] 0.542 Laboratory fndings Spo2 (%) 100.00 [100.00, 100.00] 100.00 [100.00, 100.00] 100.00 [100.00, 100.00] 0.037 Calcium_free (mmol/L) 1.13 [1.08, 1.19] 1.13 [1.08, 1.19] 1.14 [1.08, 1.20] 0.007 WBC (K/uL) 12.70 [8.70, 17.80] 12.30 [8.30, 17.60] 13.50 [10.00, 18.40] <0.001 Hematocrit % 31.80 [28.20, 36.00] 30.90 [27.70, 34.80] 34.60 [31.10, 38.60] <0.001 MCH (pg) 30.50 [28.90, 31.90] 30.40 [28.70, 31.80] 30.70 [29.40, 32.00] <0.001 MCV (fL) 93.00 [88.00, 97.00] 93.00 [88.00, 98.00] 92.00 [88.00, 96.00] 0.005 MCHC (%) 33.20 [32.00, 34.30] 32.90 [31.90, 34.10] 33.90 [32.70, 34.90] <0.001 RDW (%) 15.60 [14.30, 17.10] 16.00 [14.60, 17.50] 14.70 [13.70, 15.60] <0.001 PLT (K/uL) 189.00 [125.00, 258.00] 190.00 [121.00, 261.00] 188.00 [139.00, 248.00] 0.451 RBC (m/uL) 3.48 [3.05, 3.98] 3.37 [2.97, 3.85] 3.80 [3.39, 4.26] <0.001 Alb (g/dl) 2.90 [2.60, 3.30] 2.90 [2.50, 3.30] 3.10 [2.70, 3.40] <0.001 Creatinine (mg/dl) 1.30 [0.90, 2.30] 1.30 [0.80, 2.20] 1.50 [1.00, 2.40] <0.001 BUN (mg/dl) 28.00 [17.00, 43.00] 29.00 [18.00, 45.00] 25.00 [16.00, 38.00] <0.001 Aniongap 16.00 [13.00, 19.00] 16.00 [13.00, 18.00] 17.00 [14.00, 20.00] <0.001 PT (seconds) 15.30 [13.30, 19.10] 15.50 [13.30, 19.50] 14.90 [13.00, 17.90] <0.001 PTT (seconds) 33.50 [28.70, 42.48] 33.70 [28.90, 42.30] 32.70 [28.30, 42.90] 0.139 INR 1.40 [1.20, 1.80] 1.40 [1.20, 1.80] 1.30 [1.20, 1.70] <0.001 CK_CKMB_ratio (U/L) 33.00 [14.00, 92.00] 23.00 [11.00, 54.00] 111.00 [57.00, 210.00] <0.001 ALT (U/L) 33.00 [18.00, 75.75] 29.00 [16.00, 60.00] 58.00 [29.00, 161.00] <0.001 AST (U/L) 50.00 [27.00, 120.00] 40.00 [24.00, 84.00] 117.00 [54.00, 335.00] <0.001 ALP (U/L) 88.00 [62.00, 133.00] 95.00 [67.00, 142.00] 66.00 [49.00, 95.00] <0.001 Bilirubin_total (mg/dl) 0.80 [0.40, 1.70] 0.80 [0.40, 1.80] 0.70 [0.40, 1.40] <0.001 LDH (U/L) 308.00 [218.00, 477.00] 277.00 [205.00, 408.00] 453.00 [302.00, 702.00] <0.001 Chloride (mg/dl) 106.00 [102.00, 110.00] 105.00 [101.00, 110.00] 108.00 [104.00, 112.00] <0.001 Glucose (mg/dl) 155.50 [121.00, 204.00] 150.00 [119.00, 198.00] 171.00 [132.00, 224.00] <0.001 Bicarbonate (g/dl) 24.00 [21.00, 26.00] 24.00 [21.00, 27.00] 23.00 [21.00, 26.00] <0.001 Hb (g/dl) 10.50 [9.20, 11.90] 10.10 [8.90, 11.40] 11.70 [10.40, 12.90] <0.001 K (mEq/L) 4.40 [4.00, 4.90] 4.30 [4.00, 4.80] 4.60 [4.10, 5.20] <0.001 Na (mEq/L) 140.00 [137.00, 143.00] 139.00 [136.00, 142.00] 141.00 [138.00, 144.00] <0.001 Mg (mg/dL) 2.20 [1.90, 2.40] 2.20 [1.90, 2.40] 2.20 [2.00, 2.50] <0.001 Ca(mg/dL) 8.40 [7.90, 8.80] 8.40 [7.90, 8.90] 8.30 [7.90, 8.70] <0.001 P (mg/dL) 4.10 [3.30, 5.10] 4.00 [3.20, 4.90] 4.40 [3.50, 5.40] <0.001 Input_24h_sum (ml) 4964.50 [2649.00, 8077.00] 4255.00 [2301.00, 7067.00] 7327.00 [4617.00, 10827.00] <0.001 Output_24h_sum (ml) 1860.00 [1050.00, 3033.75] 1770.00 [994.00, 2810.00] 2340.00 [1306.50, 3580.00] <0.001 Output_urine_sum (ml) 1302.50 [743.50, 2050.00] 1270.00 [729.00, 1975.00] 1430.00 [830.00, 2240.00] <0.001 Comorbidity, n (%) Smoker (%) 328 ( 8.67) 252 ( 8.77) 76 ( 8.36) 0.752 Alcohol_abuse (%) 59 ( 1.56) 41 ( 1.43) 18 ( 1.98) 0.308 Hypertension (%) 1391 (36.78) 1046 (36.41) 345 (37.95) 0.422 Diabetes (%) 1204 (31.84) 978 (34.04) 226 (24.86) <0.001 Myocardial_infarct (%) 279 ( 7.38) 224 ( 7.80) 55 ( 6.05) 0.092 Congestive_heart_failure (%) 1230 (32.52) 1026 (35.71) 204 (22.44) <0.001 Mild_liver_disease (%) 890 (23.53) 697 (24.26) 193 (21.23) 0.067 Severe_liver_disease (%) 472 (12.48) 426 (14.83) 46 ( 5.06) <0.001 Renal_disease (%) 1016 (26.86) 856 (29.79) 160 (17.60) <0.001 Chronic_pulmonary_disease (%) 1059 (28.00) 836 (29.10) 223 (24.53) 0.009 Cerebrovascular_disease (%) 550 (14.54) 405 (14.10) 145 (15.95) 0.184 Peripheral_vascular_disease (%) 504 (13.33) 373 (12.98) 131 (14.41) 0.294 Dementia (%) 123 ( 3.25) 105 ( 3.65) 18 ( 1.98) 0.018 Peptic_ulcer_disease (%) 162 ( 4.28) 140 ( 4.87) 22 ( 2.42) 0.002 Paraplegia (%) 197 ( 5.21) 146 ( 5.08) 51 ( 5.61) 0.589 Malignant_cancer (%) 578 (15.28) 509 (17.72) 69 ( 7.59) <0.001 Metastatic_solid_tumor (%) 179 ( 4.73) 151 ( 5.26) 28 ( 3.08) 0.009 Aids (%) 41 ( 1.08) 30 ( 1.04) 11 ( 1.21) 0.812 Rheumatic_disease (%) 171 ( 4.52) 144 ( 5.01) 27 ( 2.97) 0.013 AKI (%) 3224 (85.25) 2422 (84.30) 802 (88.23) 0.004 Treatment status InvasiveVent (%) 2348 (62.08) 1588 (55.27) 760 (83.61) <0.001 CPR (%) 76 ( 2.01) 45 ( 1.57) 31 ( 3.41) 0.001 CRRT (%) 555 (14.67) 363 (12.63) 192 (21.12) <0.001 RRT (%) 772 (20.41) 544 (18.93) 228 (25.08) <0.001 Data are shown as median with interquartile range (IQR) for continuous variables and number with percentage for categorical variables SOFA: Sequential Organ Failure Assessment, SAPSII: Simplified Acute Physiology Score II, APSIII: Acute Physiology Score III, OASIS: Oxford Acute Severity of Illness Score, GCS: Glasgow Coma Scale, SIRS: Systemic Inflammatory Response Syndrome, LODS: Logistic Organ Dysfunction System, MELD: Model for End-Stage Liver Disease, Charlson: Charlson Comorbidity Index, RM: Rhabdomyolysis, BMI: Body Mass Index, HR: Heart Rate, RR: Respiratory Rate, SBP: Systolic Blood Pressure, DBP: Diastolic Blood Pressure, MBP: Mean Blood Pressure, SpO2: Oxygen Saturation, WBC: White Blood Cell, MCH: Mean Corpuscular Hemoglobin, MCV: Mean Corpuscular Volume, MCHC: Mean Corpuscular Hemoglobin Concentration, RDW: Red Cell Distribution Width, PLT: Platelet, RBC: Red Blood Cell, Alb: Albumin, BUN: Blood Urea Nitrogen, PT: Prothrombin Time, PTT: Partial Thromboplastin Time, INR: International Normalized Ratio, ALT: Alanine Aminotransferase, AST: Aspartate Aminotransferase, ALP: Alkaline Phosphatase, LDH: Lactate Dehydrogenase, Hb: Hemoglobin, AKI: Acute Kidney Injury, CPR: Cardiopulmonary Resuscitation, CRRT: Continuous Renal Replacement Therapy, RRT: Renal Replacement Therapy, IQR: Interquartile Range Table 2 Performance of 6 machine learning-based models for predicting ICU admission in the validation set Model AUC 95% CI Lower 95% CI Upper Accuracy Precision Sensitivity Specificity F1 Score Kappa Youden's J PPV NPV Logistic 0.877 0.856 0.898 0.826 0.712 0.463 0.941 0.561 0.459 0.404 0.712 0.847 Decision Tree 0.886 0.864 0.907 0.853 0.709 0.662 0.914 0.684 0.589 0.576 0.709 0.895 Random Forest 0.911 0.891 0.930 0.876 0.799 0.643 0.949 0.713 0.635 0.592 0.799 0.894 XGBoost 0.924 0.907 0.941 0.883 0.791 0.695 0.942 0.740 0.664 0.637 0.791 0.907 SVM 0.885 0.866 0.905 0.825 0.720 0.445 0.945 0.550 0.449 0.390 0.720 0.844 ANN 0.911 0.893 0.929 0.865 0.772 0.621 0.942 0.688 0.603 0.563 0.772 0.887 AUC: area under the receiver operating characteristic curve; XGBoost: eXtreme gradient boosting; SVM: Support Vector Machine ; ANN: Artificial Neural Network Additional Declarations No competing interests reported. Supplementary Files ANNconfusionmatrix.pdf Logisticconfusionmatrix.pdf SVMconfusionmatrix.pdf RandomForestconfusionmatrix.pdf DecisionTreeconfusionmatrix.pdf XGBoostconfusionmatrix.pdf file.docx file.xlsx file.pdf Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 27 Jan, 2026 Reviews received at journal 26 Dec, 2025 Reviews received at journal 16 Dec, 2025 Reviewers agreed at journal 13 Dec, 2025 Reviewers agreed at journal 09 Dec, 2025 Reviewers invited by journal 05 Dec, 2025 Editor invited by journal 10 Nov, 2025 Editor assigned by journal 05 Nov, 2025 Submission checks completed at journal 05 Nov, 2025 First submitted to journal 20 Oct, 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-7904814","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":557725433,"identity":"74fedcf5-0e6c-4bce-ba19-7ec2e277e5cc","order_by":0,"name":"Xiangyi Zhou","email":"","orcid":"","institution":"First Affiliated Hospital of Chongqing Medical University","correspondingAuthor":false,"prefix":"","firstName":"Xiangyi","middleName":"","lastName":"Zhou","suffix":""},{"id":557725435,"identity":"d13e8db9-d50e-42a3-b535-e61f8117b4ab","order_by":1,"name":"Hongbin Deng","email":"","orcid":"","institution":"Nanjing General Hospital of Nanjing Military Command","correspondingAuthor":false,"prefix":"","firstName":"Hongbin","middleName":"","lastName":"Deng","suffix":""},{"id":557725436,"identity":"cdf606db-1e67-41ee-9a6d-b1f7d1803b57","order_by":2,"name":"Daqian Gu","email":"","orcid":"","institution":"Nanjing General Hospital of Nanjing Military Command","correspondingAuthor":false,"prefix":"","firstName":"Daqian","middleName":"","lastName":"Gu","suffix":""},{"id":557725437,"identity":"6851ae1a-6883-4501-af37-d2485ffc0838","order_by":3,"name":"Fachun Zhou","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAz0lEQVRIiWNgGAWjYJCCDwwGNnL87I2NDz4QqYNxBkNBmrFkz+FmwxnEa/lwONFgRnqbNAcx6vlnpD9s+GFwOMFA8mGDNAODnZxuAwEtEjcSEht7DNLzzKUTG4wLGJKNzQ4Q0GIgkXD8MYOBdbHl7MSG5BkMBxK3EdaS2NjMYMCcuOHmwYbDPMRpSWYEanFO3HCDsbGZKC0SZ54xAv0CCuTEZsYZBkT4hb8dFGJ/QFF5/PmPDxV2cgS1MAgkoLiTkHKwNQQNHQWjYBSMghEPAFOyRxbEWfHpAAAAAElFTkSuQmCC","orcid":"","institution":"First Affiliated Hospital of Chongqing Medical University","correspondingAuthor":true,"prefix":"","firstName":"Fachun","middleName":"","lastName":"Zhou","suffix":""}],"badges":[],"createdAt":"2025-10-20 10:38:20","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7904814/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7904814/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":97900596,"identity":"ddf33694-5689-4c87-9d1f-f7354d37da6a","added_by":"auto","created_at":"2025-12-10 15:45:40","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1138112,"visible":true,"origin":"","legend":"","description":"","filename":"AMachineLearningBasedModelforPredictingRhabdomyolysisinPatientsWithSepsisv1.1.docx","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/e7866db2a9458b8b38bfd45c.docx"},{"id":97900589,"identity":"e199f201-ae2a-4f35-8293-925a8bf593a4","added_by":"auto","created_at":"2025-12-10 15:45:39","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1164176,"visible":true,"origin":"","legend":"","description":"","filename":"AMachineLearningBasedModelforPredictingRhabdomyolysisinPatientsWithSepsisv1.docx","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/711772c633f2d4bfc8f9547c.docx"},{"id":97899630,"identity":"12b7dd66-ade1-4959-8835-19ca25fd8927","added_by":"auto","created_at":"2025-12-10 15:44:46","extension":"xlsx","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16716,"visible":true,"origin":"","legend":"","description":"","filename":"Table1.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/414c520fc8ef8fdaa4c2cfa3.xlsx"},{"id":98421013,"identity":"0bb97f74-167f-4614-a407-c5cf8ed1ef56","added_by":"auto","created_at":"2025-12-17 16:22:11","extension":"xlsx","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10257,"visible":true,"origin":"","legend":"","description":"","filename":"Table2.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/09274b9f71f1ad9dc6ecd0e6.xlsx"},{"id":97868226,"identity":"9c1a6131-e6bd-49ad-a56e-780b0ccc1e78","added_by":"auto","created_at":"2025-12-10 09:55:45","extension":"json","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5590,"visible":true,"origin":"","legend":"","description":"","filename":"f25d25897e204f0189062321e4f4b735.json","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/0845808cc615ce1ea1efdd8d.json"},{"id":97868220,"identity":"b7843b14-1225-402b-b441-e727c2a4ec3a","added_by":"auto","created_at":"2025-12-10 09:55:45","extension":"pdf","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":19722,"visible":true,"origin":"","legend":"","description":"","filename":"ANNconfusionmatrix.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/1f3a99ecbb02c6d5d198099f.pdf"},{"id":97900901,"identity":"4a442e84-6909-4847-a896-4fb472da5ae6","added_by":"auto","created_at":"2025-12-10 15:46:02","extension":"pdf","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20430,"visible":true,"origin":"","legend":"","description":"","filename":"DecisionTreeconfusionmatrix.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/8f24667bc0061d082aa76c4a.pdf"},{"id":97900514,"identity":"4a9ba252-d02a-4921-b06b-ddef47ccb2e4","added_by":"auto","created_at":"2025-12-10 15:45:36","extension":"pdf","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20819,"visible":true,"origin":"","legend":"","description":"","filename":"Logisticconfusionmatrix.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/5079bce69e4138e48bd758ab.pdf"},{"id":97868232,"identity":"a2b9f722-9c36-43a0-8b2e-62b26c1d87ba","added_by":"auto","created_at":"2025-12-10 09:55:46","extension":"pdf","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20624,"visible":true,"origin":"","legend":"","description":"","filename":"RandomForestconfusionmatrix.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/5cec01b04bc106b5bb7215f8.pdf"},{"id":97900448,"identity":"2daecb7f-09ed-4813-bc39-b838c1d226b7","added_by":"auto","created_at":"2025-12-10 15:45:32","extension":"pdf","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20633,"visible":true,"origin":"","legend":"","description":"","filename":"SVMconfusionmatrix.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/670f5c2e898f210c28a41655.pdf"},{"id":97898801,"identity":"4e3657aa-ddf7-418b-a25f-d6552ed30551","added_by":"auto","created_at":"2025-12-10 15:39:46","extension":"pdf","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":21334,"visible":true,"origin":"","legend":"","description":"","filename":"XGBoostconfusionmatrix.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/4b5c39faf78a6f740de79046.pdf"},{"id":97868235,"identity":"b299c3f2-0954-4d64-a5cb-2ad28f44b231","added_by":"auto","created_at":"2025-12-10 09:55:46","extension":"xlsx","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10665,"visible":true,"origin":"","legend":"","description":"","filename":"file.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/54abcae0da0b8b34022361ca.xlsx"},{"id":97899389,"identity":"c19b48d3-6232-455a-86a2-0a81052c1fa3","added_by":"auto","created_at":"2025-12-10 15:43:30","extension":"pdf","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7545,"visible":true,"origin":"","legend":"","description":"","filename":"file.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/46bcb219c078d1a58ae4f334.pdf"},{"id":97899549,"identity":"650f1afe-fef4-481a-a496-fc39a7c8dd81","added_by":"auto","created_at":"2025-12-10 15:44:43","extension":"docx","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10381,"visible":true,"origin":"","legend":"","description":"","filename":"file.docx","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/71047e4317033c1d782f24f7.docx"},{"id":97868234,"identity":"5820529d-bafd-4507-898e-a5ccd33de301","added_by":"auto","created_at":"2025-12-10 09:55:46","extension":"xml","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":240420,"visible":true,"origin":"","legend":"","description":"","filename":"f25d25897e204f0189062321e4f4b7351enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/7b1e64303689bb1e181c6b7b.xml"},{"id":97868229,"identity":"00335bc9-d62c-43b6-8a28-27dae65f7c27","added_by":"auto","created_at":"2025-12-10 09:55:46","extension":"pdf","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1146521,"visible":true,"origin":"","legend":"","description":"","filename":"fig14.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/c55f78ff5a72ab37d405349b.pdf"},{"id":97900007,"identity":"fadf8960-1a28-445f-8ae7-80d7394ff8fc","added_by":"auto","created_at":"2025-12-10 15:45:09","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":97799,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/66d909489b25fe7684b1840d.png"},{"id":97868225,"identity":"8bd3832b-8a0e-4e45-8b3e-6fc9592a4f6b","added_by":"auto","created_at":"2025-12-10 09:55:45","extension":"png","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":25284,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/4bf4f6e94c04eefb2d1a3535.png"},{"id":97900318,"identity":"f5f818b4-61b4-454a-bdcb-7368f2d5b1d1","added_by":"auto","created_at":"2025-12-10 15:45:22","extension":"png","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":54688,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/7e6f5b35550c372e857812f9.png"},{"id":97868241,"identity":"3902b043-5d43-41a6-bfa6-3ea46b791f45","added_by":"auto","created_at":"2025-12-10 09:55:46","extension":"png","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":100531,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/bd0cb6fd7f0a9cb39ab8f9d4.png"},{"id":97899650,"identity":"b52333e8-91bd-49a7-8ace-94d9dba7eb4a","added_by":"auto","created_at":"2025-12-10 15:44:48","extension":"png","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":22611,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/5ca67dc537277c9927c3c573.png"},{"id":97868242,"identity":"c27d926a-b9be-49be-8340-ec5fa8ac834f","added_by":"auto","created_at":"2025-12-10 09:55:46","extension":"png","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":53021,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/654be1df2fd1b4214172d5fe.png"},{"id":97900557,"identity":"8b1b04ca-142a-4558-9c09-573ecc6318ef","added_by":"auto","created_at":"2025-12-10 15:45:37","extension":"png","order_by":30,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":54688,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/4f0cb87e4478090e6d5f2571.png"},{"id":97899526,"identity":"b88c1141-7828-41c4-86c0-0c0f2dc5448e","added_by":"auto","created_at":"2025-12-10 15:44:40","extension":"png","order_by":31,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":100531,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/8dd7854e4c3cbf15843c734e.png"},{"id":97868247,"identity":"92d64427-4309-48aa-800f-5c28ca841b64","added_by":"auto","created_at":"2025-12-10 09:55:46","extension":"png","order_by":32,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":22611,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/619521243d6a04f37766d01d.png"},{"id":97899623,"identity":"11ea88d4-e154-4bb7-99ef-447d5796dc55","added_by":"auto","created_at":"2025-12-10 15:44:45","extension":"xml","order_by":33,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":237483,"visible":true,"origin":"","legend":"","description":"","filename":"f25d25897e204f0189062321e4f4b7351structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/6aeef9f05251377e398aaeff.xml"},{"id":97900474,"identity":"26c4a292-a1a1-4cf9-869d-3d186b0fa5b5","added_by":"auto","created_at":"2025-12-10 15:45:33","extension":"html","order_by":34,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":251807,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/611af11d59a3712da54f38d2.html"},{"id":97900652,"identity":"13c812af-fba5-4a6e-91cb-e2f96bb7be04","added_by":"auto","created_at":"2025-12-10 15:45:42","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":81839,"visible":true,"origin":"","legend":"\u003cp\u003eFlowchart of patient selection\u003c/p\u003e\n\u003cp\u003eRM: rhabdomyolysis; CK: creatine kinase; AMI: acute myocardial infarction; CHF: congestive heart failure; CKD: chronic kidney disease; CRF: chronic renal failure; CLF: chronic liver failure; DM: dermatomyositis; PM: polymyositis; SHAP: Shapley Additive explanation\u003cstrong\u003e.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/a46c1d0c2e38dffb14a90f5c.png"},{"id":97900550,"identity":"f0fc5b06-5499-4fcc-adf6-a46491386fb7","added_by":"auto","created_at":"2025-12-10 15:45:36","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":226965,"visible":true,"origin":"","legend":"\u003cp\u003eFeatures selected by Boruta, Lasso and univariate analysis.\u003c/p\u003e\n\u003cp\u003eA. The optimal lambda selection in the Lasso regression with 10-fold cross-validation. Misclassification errors of different variables against log(lambda) are revealed. The two vertical dashed lines represent the optimal value under the minimum criterion and 1-SE criterion, respectively. The \"lambda\" is the tuning parameter. A total of 33 predictors with non-zero coefficients are identified. \u003cstrong\u003eB.\u003c/strong\u003e The Lasso regression coefficient profiles of all baseline characteristics. \u003cstrong\u003eC. \u003c/strong\u003eVariables selected by Boruta algorithm. The minimum, average and maximum shadow score are shown in blue. \u003cstrong\u003eD. \u003c/strong\u003eIn terms of the score of feature importance, the 22 variables in green are regarded as important variables, while yellow are neutral and red are rejected. \u003cstrong\u003eE.\u003c/strong\u003e The Venn diagram of features selected by Boruta, Lasso and univariate analysis. The intersection results of three methods yield 10 clinical characteristics. SE, standard error; Lasso, least absolute shrinkage and selection operator.\u003c/p\u003e","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/943f19562946229dd32d1959.png"},{"id":97900396,"identity":"22a62d2b-cfaa-4db0-8303-1877ced9676a","added_by":"auto","created_at":"2025-12-10 15:45:28","extension":"jpeg","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":489511,"visible":true,"origin":"","legend":"\u003cp\u003ePerformance evaluation of machine learning models for predicting clinical outcomes in the validation set.\u003c/p\u003e\n\u003cp\u003e(A) \u0026nbsp;Calibration curves of six machine learning models with their Brier scores and 95% confidence intervals. The gray line represents perfect calibration. (B) Decision curve analysis showing the net benefit of each model across different threshold probabilities. The gray lines represent the strategies of treating all patients and treating none. (C) Receiver operating characteristic curves with area under the curve values and 95% confidence intervals for each model. AUC, area under the curve; CI, confidence interval; Logistic, logistic regression; Decision Tree, decision tree algorithm; Random Forest, random forest algorithm; XGBoost, extreme gradient boosting; SVM, support vector machine; ANN, artificial neural network.\u003c/p\u003e","description":"","filename":"floatimage3.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/4cfc905a73c24792f250620d.jpeg"},{"id":97900913,"identity":"c9d87e7f-66ef-4809-81a7-edbcfe256ac7","added_by":"auto","created_at":"2025-12-10 15:46:03","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":93668,"visible":true,"origin":"","legend":"\u003cp\u003eSHAP (Shapley Additive Explanations) analysis of the XGBoost model for predicting clinical outcomes.\u003c/p\u003e\n\u003cp\u003e(A) \u0026nbsp;Bar plot showing the mean absolute SHAP values for each predictor in descending order of importance. CK/CKMB, AST, and InvasiveVent are the top three most important features. (B) Beeswarm plot displaying the distribution of SHAP values for each feature across all samples. Each point represents a single patient, with color indicating the feature value (red: low, blue: high). The horizontal dispersion shows the impact of each feature on model output. (C) Waterfall plot for a representative patient fromRM, showing how each feature contributes to the final prediction. The baseline expectation E[f(X)] is 0.758, while the model output f(x) is 0.957. (D) Waterfall plot for a representative patient from non-RM, with baseline expectation E[f(X)] of 0.242 and model output f(x) of 0.043. Positive SHAP values push the prediction higher, while negative values push it lower. SHAP, Shapley Additive Explanations; ICU, intensive care unit; CK/CKMB, creatine kinase and its MB isoenzyme ratio; AST, aspartate aminotransferase; LDH, lactate dehydrogenase; Alb, albumin; P, phosphorus; CPR, cardiopulmonary resuscitation.\u003c/p\u003e","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/3a7ca93abb32845f92e3d2c2.png"},{"id":97868238,"identity":"08b49b4e-5686-4041-940f-31223c69b079","added_by":"auto","created_at":"2025-12-10 09:55:46","extension":"png","order_by":22,"title":"Figure 22","display":"","copyAsset":false,"role":"figure","size":226965,"visible":true,"origin":"","legend":"\u003cp\u003eFeatures selected by Boruta, Lasso and univariate analysis.\u003c/p\u003e\n\u003cp\u003eA. The optimal lambda selection in the Lasso regression with 10-fold cross-validation. Misclassification errors of different variables against log(lambda) are revealed. The two vertical dashed lines represent the optimal value under the minimum criterion and 1-SE criterion, respectively. The \"lambda\" is the tuning parameter. A total of 33 predictors with non-zero coefficients are identified. \u003cstrong\u003eB.\u003c/strong\u003e The Lasso regression coefficient profiles of all baseline characteristics. \u003cstrong\u003eC. \u003c/strong\u003eVariables selected by Boruta algorithm. The minimum, average and maximum shadow score are shown in blue. \u003cstrong\u003eD. \u003c/strong\u003eIn terms of the score of feature importance, the 22 variables in green are regarded as important variables, while yellow are neutral and red are rejected. \u003cstrong\u003eE.\u003c/strong\u003e The Venn diagram of features selected by Boruta, Lasso and univariate analysis. The intersection results of three methods yield 10 clinical characteristics. SE, standard error; Lasso, least absolute shrinkage and selection operator.\u003c/p\u003e","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/652d393b13bf25a654676b4c.png"},{"id":97900927,"identity":"9f1eaf70-b2d2-4bee-8cf7-1fd800a0161f","added_by":"auto","created_at":"2025-12-10 15:46:08","extension":"jpeg","order_by":23,"title":"Figure 23","display":"","copyAsset":false,"role":"figure","size":489511,"visible":true,"origin":"","legend":"\u003cp\u003ePerformance evaluation of machine learning models for predicting clinical outcomes in the validation set.\u003c/p\u003e\n\u003cp\u003e(A) \u0026nbsp;Calibration curves of six machine learning models with their Brier scores and 95% confidence intervals. The gray line represents perfect calibration. (B) Decision curve analysis showing the net benefit of each model across different threshold probabilities. The gray lines represent the strategies of treating all patients and treating none. (C) Receiver operating characteristic curves with area under the curve values and 95% confidence intervals for each model. AUC, area under the curve; CI, confidence interval; Logistic, logistic regression; Decision Tree, decision tree algorithm; Random Forest, random forest algorithm; XGBoost, extreme gradient boosting; SVM, support vector machine; ANN, artificial neural network.\u003c/p\u003e","description":"","filename":"floatimage3.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/8e4ca544f1948fc39ad9e198.jpeg"},{"id":97868231,"identity":"7bcaa55e-6a5e-45f9-afea-0b6f277a0d20","added_by":"auto","created_at":"2025-12-10 09:55:46","extension":"png","order_by":24,"title":"Figure 24","display":"","copyAsset":false,"role":"figure","size":93668,"visible":true,"origin":"","legend":"\u003cp\u003eSHAP (Shapley Additive Explanations) analysis of the XGBoost model for predicting clinical outcomes.\u003c/p\u003e\n\u003cp\u003e(A) \u0026nbsp;Bar plot showing the mean absolute SHAP values for each predictor in descending order of importance. CK/CKMB, AST, and InvasiveVent are the top three most important features. (B) Beeswarm plot displaying the distribution of SHAP values for each feature across all samples. Each point represents a single patient, with color indicating the feature value (red: low, blue: high). The horizontal dispersion shows the impact of each feature on model output. (C) Waterfall plot for a representative patient fromRM, showing how each feature contributes to the final prediction. The baseline expectation E[f(X)] is 0.758, while the model output f(x) is 0.957. (D) Waterfall plot for a representative patient from non-RM, with baseline expectation E[f(X)] of 0.242 and model output f(x) of 0.043. Positive SHAP values push the prediction higher, while negative values push it lower. SHAP, Shapley Additive Explanations; ICU, intensive care unit; CK/CKMB, creatine kinase and its MB isoenzyme ratio; AST, aspartate aminotransferase; LDH, lactate dehydrogenase; Alb, albumin; P, phosphorus; CPR, cardiopulmonary resuscitation.\u003c/p\u003e","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/bbcd59f75962b6928ba8d6b9.png"},{"id":98443198,"identity":"0a957cdc-9e62-4ae2-a132-7ea3b7503366","added_by":"auto","created_at":"2025-12-17 17:12:42","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3128520,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/553c12d4-a2d0-45c3-bf27-ed9ff2641003.pdf"},{"id":97900460,"identity":"2269a1cf-aa67-4f92-8a37-c58716d84fd9","added_by":"auto","created_at":"2025-12-10 15:45:32","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":19722,"visible":true,"origin":"","legend":"","description":"","filename":"ANNconfusionmatrix.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/6adb993378e2c51bdff37f68.pdf"},{"id":97868204,"identity":"0cdfe3c4-1ee5-43b4-92a2-a28b755295b8","added_by":"auto","created_at":"2025-12-10 09:55:45","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":20819,"visible":true,"origin":"","legend":"","description":"","filename":"Logisticconfusionmatrix.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/cb9165ca7fad32ddeeac08ec.pdf"},{"id":97868211,"identity":"b2a38d1b-fd5e-442e-9139-1af1e243c45d","added_by":"auto","created_at":"2025-12-10 09:55:45","extension":"pdf","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":20633,"visible":true,"origin":"","legend":"","description":"","filename":"SVMconfusionmatrix.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/7508af321437f633505badb7.pdf"},{"id":97900542,"identity":"4c766f00-0d01-49b2-8a11-d437f06b46db","added_by":"auto","created_at":"2025-12-10 15:45:36","extension":"pdf","order_by":4,"title":"","display":"","copyAsset":false,"role":"supplement","size":20624,"visible":true,"origin":"","legend":"","description":"","filename":"RandomForestconfusionmatrix.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/edf94c57d700ff11c56430e8.pdf"},{"id":97868219,"identity":"09b20d0a-2159-494b-b286-39f686c60637","added_by":"auto","created_at":"2025-12-10 09:55:45","extension":"pdf","order_by":5,"title":"","display":"","copyAsset":false,"role":"supplement","size":20430,"visible":true,"origin":"","legend":"","description":"","filename":"DecisionTreeconfusionmatrix.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/b9bfe622a64d30228ecdaec5.pdf"},{"id":97899699,"identity":"bb5dbf83-52e7-4a5c-b9fb-c68b9094069e","added_by":"auto","created_at":"2025-12-10 15:44:50","extension":"pdf","order_by":6,"title":"","display":"","copyAsset":false,"role":"supplement","size":21334,"visible":true,"origin":"","legend":"","description":"","filename":"XGBoostconfusionmatrix.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/daf58aae7add19c8160fecad.pdf"},{"id":97900468,"identity":"d5c5f868-f2c2-4867-bf80-9accfba07a5f","added_by":"auto","created_at":"2025-12-10 15:45:33","extension":"docx","order_by":7,"title":"","display":"","copyAsset":false,"role":"supplement","size":10381,"visible":true,"origin":"","legend":"","description":"","filename":"file.docx","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/8155da097d7f1591be20f514.docx"},{"id":97868223,"identity":"9fba19df-0fd2-45f4-8317-99da4ff27b60","added_by":"auto","created_at":"2025-12-10 09:55:45","extension":"xlsx","order_by":8,"title":"","display":"","copyAsset":false,"role":"supplement","size":10665,"visible":true,"origin":"","legend":"","description":"","filename":"file.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/f9f2f63b7adf107a9780c8ce.xlsx"},{"id":97899703,"identity":"f741a36d-d0f0-4b6d-afe6-fa4e2e733979","added_by":"auto","created_at":"2025-12-10 15:44:50","extension":"pdf","order_by":9,"title":"","display":"","copyAsset":false,"role":"supplement","size":7545,"visible":true,"origin":"","legend":"","description":"","filename":"file.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7904814/v1/4e678732300b7c72abddc46f.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Machine Learning-Based Model for Predicting Rhabdomyolysis in Patients With Sepsis","fulltext":[{"header":"Introduction","content":"\u003cp\u003eSepsis remains a major cause of morbidity and mortality in the intensive care unit (ICU), characterized by dysregulated host response and multiple organ dysfunction\u003csup\u003e\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e\u003c/sup\u003e. Beyond its well-recognized complications, sepsis has been increasingly associated with skeletal muscle injury, particularly rhabdomyolysis\u003csup\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e,\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e\u003c/sup\u003e. Rhabdomyolysis is defined as the breakdown of skeletal muscle fibers with subsequent release of intracellular components such as creatine kinase, myoglobin, and electrolytes into the circulation, leading to severe metabolic disturbances, acute kidney injury, and worsened clinical outcomes\u003csup\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e,\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e\u003c/sup\u003e. Previous reports suggest that systemic inflammation, tissue hypoperfusion, mitochondrial dysfunction, and exposure to myo-/nephrotoxic agents may synergistically contribute to rhabdomyolysis in septic patients\u003csup\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e,\u003cspan additionalcitationids=\"CR6\" citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e\u003c/sup\u003e. Despite its clinical significance, rhabdomyolysis in the context of critical illness is often challenging to recognize early because classic symptoms are nonspecific and creatine kinase elevation is typically detected after muscle injury has occurred\u003csup\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e,\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e\u003cp\u003eEarly identification of septic patients at risk of rhabdomyolysis is of critical importance for timely interventions, including optimized hemodynamic resuscitation, avoidance of myotoxic drugs, and early renal protection strategies\u003csup\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e,\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e\u003c/sup\u003e. Conventional diagnostic approaches rely mainly on elevated creatine kinase levels after muscle damage has occurred, which limits the potential for early preventive measures. Furthermore, rhabdomyolysis may develop insidiously in critically ill patients, making clinical suspicion and diagnosis challenging\u003csup\u003e\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e\u003c/sup\u003e. Therefore, a reliable predictive model could help clinicians stratify risk, monitor high-risk patients more closely, and implement targeted preventive strategies before irreversible muscle injury and secondary organ damage occur.\u003c/p\u003e\u003cp\u003eIn recent years, machine learning techniques have shown great promise in healthcare by enabling the integration of large-scale, high-dimensional clinical data to generate accurate predictions and personalized risk assessments. Unlike traditional regression-based models, machine learning algorithms can capture complex nonlinear relationships and interactions among diverse clinical and laboratory variables, which are often present in sepsis pathophysiology\u003csup\u003e\u003cspan additionalcitationids=\"CR9\" citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e\u003c/sup\u003e. Several machine learning-based models have already demonstrated superior performance in predicting complications such as acute kidney injury, septic shock, and mortality\u003csup\u003e\u003cspan additionalcitationids=\"CR9 CR10 CR11 CR12\" citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e\u003c/sup\u003e. However, no predictive models specifically targeting sepsis-associated rhabdomyolysis have been systematically developed and validated to date. In this study, we aimed to construct and validate a machine learning-based predictive model for rhabdomyolysis in patients with sepsis using a large critical care database to provide clinicians with a practical tool for early risk stratification, thereby improving prevention and management strategies for this potentially life-threatening complication.\u003c/p\u003e"},{"header":"Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\u003ch2\u003eData source and study population\u003c/h2\u003e\u003cp\u003e This retrospective cohort study was conducted using data from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database, a large, publicly available critical care database that contains detailed clinical information for patients admitted to the Beth Israel Deaconess Medical Center between 2008 and 2019. Access to the database was granted after completion of the required Collaborative Institutional Training Initiative course.\u003c/p\u003e\u003cp\u003eAdult patients (\u0026ge;\u0026thinsp;18 years) with an ICU stay longer than 24 hours were eligible. Sepsis was defined according to Sepsis-3 criteria, requiring suspected infection combined with a Sequential Organ Failure Assessment (SOFA) score\u0026thinsp;\u0026ge;\u0026thinsp;2. Exclusion criteria included: (1) history of acute myocardial infarction, congestive heart failure, advanced chronic kidney disease, chronic renal failure, chronic liver failure, dermatomyositis, or polymyositis; (2) absence of creatine kinase (CK) measurements; and (3) CK\u0026thinsp;\u0026gt;\u0026thinsp;1000 U/L prior to sepsis diagnosis. For patients with multiple ICU admissions, only the first ICU stay was analyzed. The patient selection process is summarized in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\n\u003ch3\u003eOutcome definition\u003c/h3\u003e\n\u003cp\u003eThe primary outcome was sepsis-associated rhabdomyolysis (RM), defined as serum CK level exceeding 1000 U/L after the onset of sepsis. Patients were classified into RM and non-RM groups accordingly.\u003c/p\u003e\n\u003ch3\u003eFeature extraction and preprocessing\u003c/h3\u003e\n\u003cp\u003eDemographic characteristics, comorbidities, vital signs, laboratory tests, severity scores (SOFA, SAPS II, APS III, OASIS, MELD, LODS, SIRS, GCS, Charlson Comorbidity Index), and treatment interventions (mechanical ventilation, cardiopulmonary resuscitation, continuous renal replacement therapy, renal replacement therapy) were extracted within the first 24 hours of ICU admission. Continuous variables were presented as medians with interquartile ranges, while categorical variables were presented as counts and percentages. Missing data were handled using multiple imputation with chained equations.\u003c/p\u003e\n\u003ch3\u003eFeature selection\u003c/h3\u003e\n\u003cp\u003eThree complementary methods were applied to identify robust predictors of RM: (1) multivariate logistic regression, selecting variables with p\u0026thinsp;\u0026lt;\u0026thinsp;0.05; (2) least absolute shrinkage and selection operator (LASSO) regression with 10-fold cross-validation to minimize misclassification error; and (3) Boruta algorithm based on random forest importance scores. Features consistently identified by all three methods were considered final candidate predictors.\u003c/p\u003e\n\u003ch3\u003eModel development and validation\u003c/h3\u003e\n\u003cp\u003eThe study cohort was randomly split into training (70%) and validation (30%) sets. Six machine learning algorithms were developed for RM prediction: logistic regression, decision tree, random forest, extreme gradient boosting (XGBoost), support vector machine (SVM), and artificial neural network (ANN). Hyperparameters were optimized through grid search with 5-fold cross-validation within the training set.\u003c/p\u003e\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e\u003ch2\u003eModel evaluation\u003c/h2\u003e\u003cp\u003eModel performance was evaluated in the validation set using multiple metrics: area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, precision, F1 score, kappa statistic, Youden\u0026rsquo;s index, and positive and negative predictive values. Calibration curves with Brier scores and 95% confidence intervals were used to assess model calibration. Clinical utility was evaluated using decision curve analysis (DCA) (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e3\u003c/span\u003e).\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\n\u003ch3\u003eModel interpretation\u003c/h3\u003e\n\u003cp\u003eTo enhance interpretability, Shapley Additive Explanations (SHAP) analysis will be conducted on the model with the best performance. Global interpretability was assessed through mean absolute SHAP values and beeswarm plots, ranking the contribution of each predictor. Local interpretability was explored using waterfall plots to visualize the impact of individual features on the prediction for representative patients (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e4\u003c/span\u003e).\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cdiv id=\"Sec10\" class=\"Section2\"\u003e\u003ch2\u003eStatistical analysis\u003c/h2\u003e\u003cp\u003eContinuous variables were compared between groups using the Mann-Whitney U test, while categorical variables were compared using the chi-square or Fisher\u0026rsquo;s exact test, as appropriate. All statistical analyses were performed using R (version 4.2.0) and Python (version 3.9). A two-sided p value\u0026thinsp;\u0026lt;\u0026thinsp;0.05 was considered statistically significant.\u003c/p\u003e\u003c/div\u003e"},{"header":"Results","content":"\u003cdiv id=\"Sec12\" class=\"Section2\"\u003e\u003ch2\u003ePatient selection\u003c/h2\u003e\u003cp\u003eA total of 94,458 ICU admissions from the MIMIC-IV database were initially screened. After restricting to adult patients (\u0026ge;\u0026thinsp;18 years), with an ICU stay longer than 1 day, and fulfilling the Sepsis-3 criteria, 33,042 patients were eligible for further assessment. Patients with acute myocardial infarction (AMI), congestive heart failure (CHF), advanced chronic kidney disease (CKD stages 4\u0026ndash;5), chronic renal failure (CRF), chronic liver failure (CLF), dermatomyositis (DM), or polymyositis (PM) were excluded. Subsequently, patients without peak CK measurements or with CK\u0026thinsp;\u0026gt;\u0026thinsp;1000 U/L prior to the diagnosis of sepsis were also excluded. Finally, 3,782 patients were included in the analysis. The study cohort was randomly divided into a training set (70%) and an internal validation set (30%).\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec13\" class=\"Section2\"\u003e\u003ch2\u003eBaseline characteristics\u003c/h2\u003e\u003cp\u003eA total of 3782 septic patients were included in the MIMIC-IV cohort, comprising 909 patients with rhabdomyolysis (RM group) and 2873 without rhabdomyolysis (non-RM group). Significant differences in demographic, clinical, and laboratory characteristics were observed between the two groups \u003cb\u003e(\u003c/b\u003eTable\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e\u003cb\u003e)\u003c/b\u003e.\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\u003eBaseline characteristics and comparison between RM and non-RM in MIMIC database\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"6\"\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=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eDemographic characteristics\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003eOverall n\u0026thinsp;=\u0026thinsp;3782\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eNon-RM n\u0026thinsp;=\u0026thinsp;2873\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eRM n\u0026thinsp;=\u0026thinsp;909\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eP value\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e\u003cp\u003eDemographic information\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMale gender, n (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e2148 [56.80]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1504 [52.35]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e644 [70.85]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eAge(yd)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e65.00 [55.00, 75.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e67.00 [57.00, 76.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e58.00 [49.00, 69.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eHeight (cm)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e170.00 [163.00, 178.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e168.00 [163.00, 175.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e173.00 [165.00, 178.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eWeight (kg)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e79.00 [67.00, 94.50]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e77.20 [65.50, 92.30]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e84.60 [71.90, 98.60]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eBMI (kg/m\u003csup\u003e2\u003c/sup\u003e)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e27.47 [23.73, 32.03]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e27.21 [23.44, 31.74]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e28.41 [24.93, 32.86]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eLos_hospital (d)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e16.76 [9.60, 27.80]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e17.96 [10.04, 29.28]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e13.61 [7.56, 22.71]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eLos_icu (d)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e4.91 [2.44, 10.23]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e4.67 [2.28, 9.84]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e5.99 [2.84, 11.70]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eSeverity of illness\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAKI_score (median [IQR])\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e2.00 [2.00, 3.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e2.00 [2.00, 3.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e2.00 [2.00, 3.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.005\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eApsiii (median [IQR])\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e54.00 [42.00, 67.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e54.00 [43.00, 67.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e53.00 [40.00, 69.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.542\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSAPSii (median [IQR])\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e41.00 [33.00, 50.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e41.00 [33.00, 49.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e40.00 [31.00, 51.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.266\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSOFA (median [IQR])\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e7.00 [5.00, 11.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e7.00 [5.00, 10.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e8.00 [6.00, 12.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eGCS (median [IQR])\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e13.00 [9.00, 14.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e13.00 [10.00, 14.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e13.00 [9.00, 14.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.002\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSIRS (median [IQR])\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e3.00 [2.00, 4.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e3.00 [2.00, 3.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e3.00 [3.00, 4.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eLODS (median [IQR])\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e6.00 [4.00, 8.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e6.00 [4.00, 8.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e6.00 [4.00, 8.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eCharlson (median [IQR])\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e5.00 [3.00, 7.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e6.00 [4.00, 7.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e3.00 [1.00, 6.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eMELD (median [IQR])\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e17.58 [10.00, 24.68]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e18.00 [11.00, 25.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e16.57 [10.00, 24.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.038\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eOASIS (median [IQR])\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e35.00 [30.00, 40.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e35.00 [29.00, 40.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e36.00 [31.00, 42.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eVital signs\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eTemperature (℃)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e37.39 [37.00, 37.94]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e37.28 [37.00, 37.83]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e37.70 [37.20, 38.28]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.002\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHR (bpm)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e109.00 [96.00, 122.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e108.00 [96.00, 121.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e111.00 [98.00, 122.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.045\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRR (bpm)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e28.75 [25.00, 33.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e29.00 [25.00, 33.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e28.00 [24.00, 32.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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 (mmHg)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e144.00 [130.00, 158.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e143.00 [129.00, 157.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e146.00 [134.00, 162.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eDBP (mmHg)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e84.00 [73.00, 96.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e84.00 [73.00, 96.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e85.00 [76.00, 97.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eMBP (mmHg)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e99.75 [89.00, 112.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e99.00 [88.00, 111.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e103.00 [93.00, 116.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.542\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLaboratory fndings\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSpo2 (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e100.00 [100.00, 100.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e100.00 [100.00, 100.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e100.00 [100.00, 100.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.037\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCalcium_free (mmol/L)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e1.13 [1.08, 1.19]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1.13 [1.08, 1.19]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e1.14 [1.08, 1.20]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.007\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eWBC (K/uL)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e12.70 [8.70, 17.80]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e12.30 [8.30, 17.60]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e13.50 [10.00, 18.40]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eHematocrit %\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e31.80 [28.20, 36.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e30.90 [27.70, 34.80]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e34.60 [31.10, 38.60]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eMCH (pg)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e30.50 [28.90, 31.90]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e30.40 [28.70, 31.80]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e30.70 [29.40, 32.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eMCV (fL)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e93.00 [88.00, 97.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e93.00 [88.00, 98.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e92.00 [88.00, 96.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.005\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMCHC (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e33.20 [32.00, 34.30]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e32.90 [31.90, 34.10]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e33.90 [32.70, 34.90]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eRDW (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e15.60 [14.30, 17.10]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e16.00 [14.60, 17.50]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e14.70 [13.70, 15.60]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003ePLT (K/uL)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e189.00 [125.00, 258.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e190.00 [121.00, 261.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e188.00 [139.00, 248.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.451\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRBC (m/uL)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e3.48 [3.05, 3.98]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e3.37 [2.97, 3.85]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e3.80 [3.39, 4.26]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eAlb (g/dl)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e2.90 [2.60, 3.30]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e2.90 [2.50, 3.30]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e3.10 [2.70, 3.40]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eCreatinine (mg/dl)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e1.30 [0.90, 2.30]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1.30 [0.80, 2.20]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e1.50 [1.00, 2.40]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eBUN (mg/dl)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e28.00 [17.00, 43.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e29.00 [18.00, 45.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e25.00 [16.00, 38.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eAniongap\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e16.00 [13.00, 19.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e16.00 [13.00, 18.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e17.00 [14.00, 20.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003ePT (seconds)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e15.30 [13.30, 19.10]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e15.50 [13.30, 19.50]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e14.90 [13.00, 17.90]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003ePTT (seconds)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e33.50 [28.70, 42.48]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e33.70 [28.90, 42.30]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e32.70 [28.30, 42.90]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.139\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eINR\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e1.40 [1.20, 1.80]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1.40 [1.20, 1.80]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e1.30 [1.20, 1.70]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eCK_CKMB_ratio (U/L)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e33.00 [14.00, 92.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e23.00 [11.00, 54.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e111.00 [57.00, 210.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eALT (U/L)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e33.00 [18.00, 75.75]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e29.00 [16.00, 60.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e58.00 [29.00, 161.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eAST (U/L)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e50.00 [27.00, 120.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e40.00 [24.00, 84.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e117.00 [54.00, 335.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eALP (U/L)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e88.00 [62.00, 133.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e95.00 [67.00, 142.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e66.00 [49.00, 95.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eBilirubin_total (mg/dl)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e0.80 [0.40, 1.70]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.80 [0.40, 1.80]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.70 [0.40, 1.40]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eLDH (U/L)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e308.00 [218.00, 477.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e277.00 [205.00, 408.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e453.00 [302.00, 702.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eChloride (mg/dl)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e106.00 [102.00, 110.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e105.00 [101.00, 110.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e108.00 [104.00, 112.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eGlucose (mg/dl)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e155.50 [121.00, 204.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e150.00 [119.00, 198.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e171.00 [132.00, 224.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eBicarbonate (g/dl)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e24.00 [21.00, 26.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e24.00 [21.00, 27.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e23.00 [21.00, 26.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eHb (g/dl)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e10.50 [9.20, 11.90]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e10.10 [8.90, 11.40]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e11.70 [10.40, 12.90]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eK (mEq/L)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e4.40 [4.00, 4.90]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e4.30 [4.00, 4.80]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e4.60 [4.10, 5.20]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eNa (mEq/L)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e140.00 [137.00, 143.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e139.00 [136.00, 142.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e141.00 [138.00, 144.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eMg (mg/dL)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e2.20 [1.90, 2.40]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e2.20 [1.90, 2.40]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e2.20 [2.00, 2.50]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eCa(mg/dL)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e8.40 [7.90, 8.80]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e8.40 [7.90, 8.90]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e8.30 [7.90, 8.70]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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 (mg/dL)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e4.10 [3.30, 5.10]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e4.00 [3.20, 4.90]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e4.40 [3.50, 5.40]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eInput_24h_sum (ml)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e4964.50 [2649.00, 8077.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e4255.00 [2301.00, 7067.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e7327.00 [4617.00, 10827.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eOutput_24h_sum (ml)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e1860.00 [1050.00, 3033.75]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1770.00 [994.00, 2810.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e2340.00 [1306.50, 3580.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eOutput_urine_sum (ml)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e1302.50 [743.50, 2050.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1270.00 [729.00, 1975.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e1430.00 [830.00, 2240.00]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eComorbidity, n (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSmoker (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e328 ( 8.67)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e252 ( 8.77)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e76 ( 8.36)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.752\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAlcohol_abuse (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e59 ( 1.56)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e41 ( 1.43)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e18 ( 1.98)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.308\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHypertension (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e1391 (36.78)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1046 (36.41)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e345 (37.95)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.422\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eDiabetes (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e1204 (31.84)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e978 (34.04)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e226 (24.86)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eMyocardial_infarct (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e279 ( 7.38)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e224 ( 7.80)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e55 ( 6.05)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.092\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCongestive_heart_failure (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e1230 (32.52)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1026 (35.71)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e204 (22.44)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eMild_liver_disease (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e890 (23.53)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e697 (24.26)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e193 (21.23)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.067\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSevere_liver_disease (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e472 (12.48)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e426 (14.83)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e46 ( 5.06)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eRenal_disease (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e1016 (26.86)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e856 (29.79)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e160 (17.60)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eChronic_pulmonary_disease (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e1059 (28.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e836 (29.10)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e223 (24.53)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.009\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCerebrovascular_disease (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e550 (14.54)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e405 (14.10)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e145 (15.95)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.184\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePeripheral_vascular_disease (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e504 (13.33)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e373 (12.98)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e131 (14.41)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.294\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eDementia (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e123 ( 3.25)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e105 ( 3.65)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e18 ( 1.98)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.018\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePeptic_ulcer_disease (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e162 ( 4.28)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e140 ( 4.87)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e22 ( 2.42)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.002\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eParaplegia (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e197 ( 5.21)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e146 ( 5.08)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e51 ( 5.61)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.589\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMalignant_cancer (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e578 (15.28)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e509 (17.72)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e69 ( 7.59)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eMetastatic_solid_tumor (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e179 ( 4.73)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e151 ( 5.26)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e28 ( 3.08)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.009\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAids (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e41 ( 1.08)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e30 ( 1.04)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e11 ( 1.21)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.812\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRheumatic_disease (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e171 ( 4.52)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e144 ( 5.01)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e27 ( 2.97)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.013\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAKI (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e3224 (85.25)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e2422 (84.30)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e802 (88.23)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.004\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTreatment status\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eInvasiveVent (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e2348 (62.08)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1588 (55.27)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e760 (83.61)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eCPR (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e76 ( 2.01)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e45 ( 1.57)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e31 ( 3.41)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCRRT (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e555 (14.67)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e363 (12.63)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e192 (21.12)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\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\u003eRRT (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e772 (20.41)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e544 (18.93)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e228 (25.08)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"6\"\u003e\u003cem\u003eData are shown as median with interquartile range (IQR) for continuous variables and number with percentage for categorical variables\u003c/em\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd colspan=\"6\"\u003e\u003cem\u003eSOFA: Sequential Organ Failure Assessment, SAPSII: Simplified Acute Physiology Score II, APSIII: Acute Physiology Score III, OASIS: Oxford Acute Severity of Illness Score, GCS: Glasgow Coma Scale, SIRS: Systemic Inflammatory Response Syndrome, LODS: Logistic Organ Dysfunction System, MELD: Model for End-Stage Liver Disease, Charlson: Charlson Comorbidity Index, RM: Rhabdomyolysis, BMI: Body Mass Index, HR: Heart Rate, RR: Respiratory Rate, SBP: Systolic Blood Pressure, DBP: Diastolic Blood Pressure, MBP: Mean Blood Pressure, SpO2: Oxygen Saturation, WBC: White Blood Cell, MCH: Mean Corpuscular Hemoglobin, MCV: Mean Corpuscular Volume, MCHC: Mean Corpuscular Hemoglobin Concentration, RDW: Red Cell Distribution Width, PLT: Platelet, RBC: Red Blood Cell, Alb: Albumin, BUN: Blood Urea Nitrogen, PT: Prothrombin Time, PTT: Partial Thromboplastin Time, INR: International Normalized Ratio, ALT: Alanine Aminotransferase, AST: Aspartate Aminotransferase, ALP: Alkaline Phosphatase, LDH: Lactate Dehydrogenase, Hb: Hemoglobin, AKI: Acute Kidney Injury, CPR: Cardiopulmonary Resuscitation, CRRT: Continuous Renal Replacement Therapy, RRT: Renal Replacement Therapy, IQR: Interquartile Range\u003c/em\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003ePatients in the RM group were younger, more frequently male, and had higher body weight and body mass index compared with the non-RM group (all p\u0026thinsp;\u0026lt;\u0026thinsp;0.001). Although hospital length of stay was shorter in the RM group, ICU length of stay was significantly longer (both p\u0026thinsp;\u0026lt;\u0026thinsp;0.001). Regarding disease severity, RM patients had higher SOFA, SIRS, LODS, and OASIS scores, while Charlson Comorbidity Index was lower (p\u0026thinsp;\u0026lt;\u0026thinsp;0.001).\u003c/p\u003e\u003cp\u003eRM patients presented with higher temperature, heart rate, and blood pressure levels. Laboratory findings revealed substantial differences between groups. The RM group showed significantly higher white blood cell counts, hematocrit, creatinine, anion gap, liver enzymes (ALT, AST), LDH, glucose, potassium, and phosphorus levels, whereas platelet counts and bilirubin were lower. CK/CKMB ratio was markedly elevated in the RM group (111.00 [57.00\u0026ndash;210.00] vs. 23.00 [11.00\u0026ndash;54.00], p\u0026thinsp;\u0026lt;\u0026thinsp;0.001).\u003c/p\u003e\u003cp\u003eCompared with the non-RM group, RM patients had lower prevalence of diabetes, congestive heart failure, severe liver disease, and renal disease, but higher prevalence of acute kidney injury (88.23% vs. 84.30%, p\u0026thinsp;=\u0026thinsp;0.004). In terms of treatment, invasive mechanical ventilation (InvasiveVent), cardiopulmonary resuscitation (CPR), continuous renal replacement therapy (CRRT), and renal replacement therapy (RRT) were all more frequently used in the RM group (all p\u0026thinsp;\u0026lt;\u0026thinsp;0.001).\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec14\" class=\"Section2\"\u003e\u003ch2\u003eFeature selection\u003c/h2\u003e\u003cp\u003eTo identify robust predictors of sepsis-associated rhabdomyolysis, three complementary feature selection methods were applied: multivariate analysis, LASSO regression, and the Boruta algorithm \u003cb\u003e(\u003c/b\u003eFig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e2\u003c/span\u003e\u003cb\u003e)\u003c/b\u003e.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eIn the LASSO regression with 10-fold cross-validation, the misclassification error across different values of the tuning parameter was evaluated. The two vertical dashed lines indicate the optimal lambda values under the minimum and 1-standard error (SE) criteria, respectively. Using this approach, a total of 33 variables with non-zero coefficients were retained \u003cb\u003e(\u003c/b\u003eFig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e2\u003c/span\u003eA-B\u003cb\u003e)\u003c/b\u003e. The Boruta algorithm further ranked variable importance by comparing each feature with shadow features. Among all candidates, 22 variables were identified as important, while others were classified as neutral or rejected \u003cb\u003e(\u003c/b\u003eFig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e2\u003c/span\u003eC-D\u003cb\u003e)\u003c/b\u003e.\u003c/p\u003e\u003cp\u003eThe intersection of the three approaches yielded 10 overlapping predictors that were consistently associated with rhabdomyolysis, common variables are provided in the supplementary file. These variables were selected as the final candidate predictors for subsequent model construction \u003cb\u003e(\u003c/b\u003eFig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e2\u003c/span\u003eE\u003cb\u003e)\u003c/b\u003e.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec15\" class=\"Section2\"\u003e\u003ch2\u003eModel performance in the validation set\u003c/h2\u003e\u003cp\u003eThe predictive performance of six machine learning models-including logistic regression, decision tree, random forest, XGBoost, SVM, and ANN-was comprehensively evaluated in the validation set \u003cb\u003e(\u003c/b\u003eFig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e3\u003c/span\u003e\u003cb\u003e)\u003c/b\u003e.\u003c/p\u003e\u003cp\u003eCalibration analysis demonstrated that all models exhibited acceptable agreement between predicted and observed probabilities, with XGBoost and random forest showing the closest alignment to the ideal reference line and the lowest Brier scores \u003cb\u003e(\u003c/b\u003eFig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e3\u003c/span\u003eA\u003cb\u003e)\u003c/b\u003e. DCA further revealed that machine learning models, particularly XGBoost and random forest, provided greater net clinical benefit across a wide range of threshold probabilities compared with the strategies of treating all or treating none \u003cb\u003e(\u003c/b\u003eFig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e3\u003c/span\u003eB\u003cb\u003e)\u003c/b\u003e.\u003c/p\u003e\u003cp\u003eReceiver operating characteristic curves confirmed the superior discriminative performance of XGBoost, with the highest AUC, followed by random forest and ANN. Logistic regression and decision tree showed moderate discrimination, whereas SVM achieved good specificity but relatively lower sensitivity \u003cb\u003e(\u003c/b\u003eFig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e3\u003c/span\u003eC\u003cb\u003e)\u003c/b\u003e. The parameters of each model are provided in the supplementary file. Collectively, these results indicated that ensemble-based models, especially XGBoost, outperformed other approaches in predicting sepsis-associated rhabdomyolysis, The detailed performance metrics of all models in the validation set are presented in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e.\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 6 machine learning-based models for predicting ICU admission in the validation set\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"13\"\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=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" 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=\"left\" 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=\"left\" class=\"colspec\" colname=\"c11\" colnum=\"11\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c12\" colnum=\"12\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c13\" colnum=\"13\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eModel\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eAUC\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003e95% CI Lower\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003e95% CI Upper\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eAccuracy\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003ePrecision\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003eSensitivity\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c8\"\u003e\u003cp\u003eSpecificity\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c9\"\u003e\u003cp\u003eF1 Score\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c10\"\u003e\u003cp\u003eKappa\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c11\"\u003e\u003cp\u003eYouden's J\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c12\"\u003e\u003cp\u003ePPV\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c13\"\u003e\u003cp\u003eNPV\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLogistic\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.877\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.856\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.898\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.826\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.712\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.463\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.941\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.561\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.459\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e0.404\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u003cp\u003e0.712\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c13\"\u003e\u003cp\u003e0.847\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eDecision Tree\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.886\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.864\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.907\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.853\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.709\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.662\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.914\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.684\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.589\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e0.576\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u003cp\u003e0.709\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c13\"\u003e\u003cp\u003e0.895\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRandom Forest\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.911\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.891\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.930\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.876\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.799\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.643\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.949\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.713\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.635\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e0.592\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u003cp\u003e0.799\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c13\"\u003e\u003cp\u003e0.894\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eXGBoost\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.924\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.907\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.941\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.883\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.791\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.695\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.942\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.740\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.664\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e0.637\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u003cp\u003e0.791\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c13\"\u003e\u003cp\u003e0.907\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSVM\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.885\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.866\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.905\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.825\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.720\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.445\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.945\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.550\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.449\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e0.390\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u003cp\u003e0.720\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c13\"\u003e\u003cp\u003e0.844\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eANN\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.911\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.893\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.929\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.865\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.772\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.621\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.942\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.688\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.603\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e0.563\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u003cp\u003e0.772\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c13\"\u003e\u003cp\u003e0.887\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"13\"\u003e\u003cem\u003eAUC: area under the receiver operating characteristic curve; XGBoost: eXtreme gradient boosting; SVM: Support Vector Machine; ANN: Artificial Neural Network\u003c/em\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec16\" class=\"Section2\"\u003e\u003ch2\u003eModel interpretation with SHAP analysis\u003c/h2\u003e\u003cp\u003eTo enhance the interpretability of the best-performing model, SHAP analysis was applied to the XGBoost model (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e4\u003c/span\u003e).\u003c/p\u003e\u003cp\u003eThe bar plot of mean absolute SHAP values ranked the importance of each predictor, revealing that the CK/CKMB ratio, AST, and InvasiveVent were the top three contributors to model predictions \u003cb\u003e(\u003c/b\u003eFig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e4\u003c/span\u003eA\u003cb\u003e)\u003c/b\u003e. The beeswarm plot further demonstrated the distribution of SHAP values across individual patients, where higher values of CK/CKMB ratio, AST, and LDH were strongly associated with increased risk of rhabdomyolysis, while higher albumin and phosphorus levels contributed negatively to risk prediction \u003cb\u003e(\u003c/b\u003eFig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e4\u003c/span\u003eB\u003cb\u003e)\u003c/b\u003e.\u003c/p\u003e\u003cp\u003eIndividual-level explanations were provided through waterfall plots. For a representative RM patient, positive SHAP values from protective variables such as higher albumin offset the contributions from risk factors, shifting the prediction probability toward a low risk outcome (baseline expectation E[f(X)]\u0026thinsp;=\u0026thinsp;0.758; model output f(x)\u0026thinsp;=\u0026thinsp;0.957) \u003cb\u003e(\u003c/b\u003eFig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e4\u003c/span\u003eC\u003cb\u003e)\u003c/b\u003e. Conversely, for a representative non-RM patient, elevated CK/CKMB ratio, AST, and requirement of invasive ventilation exerted strong positive SHAP contributions, driving the model prediction toward high risk of rhabdomyolysis (baseline expectation E[f(X)]\u0026thinsp;=\u0026thinsp;0.242; model output f(x)\u0026thinsp;=\u0026thinsp;0.043) \u003cb\u003e(\u003c/b\u003eFig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e4\u003c/span\u003eD\u003cb\u003e)\u003c/b\u003e.\u003c/p\u003e\u003cp\u003eThese findings indicate that the XGBoost model not only achieves high predictive performance but also provides clinically interpretable insights into the relative contribution of key laboratory markers and treatment variables.\u003c/p\u003e\u003c/div\u003e"},{"header":"Discussion","content":"\u003cp\u003eRM is a life-threatening complication in ICU patients with sepsis, as it exacerbates systemic inflammation, induces acute kidney injury (AKI) via myoglobin-mediated tubular damage, and significantly increases hospital mortality\u003csup\u003e\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e,\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e\u003c/sup\u003e. In our study, AKI incidence was significantly higher in patients with RM than in non-RM patients, reflecting the bidirectional pathophysiological link between RM and AKI in sepsis. Mechanistically, myoglobin released during RM-induced skeletal muscle necrosis directly causes renal tubular obstruction, oxidative stress, and inflammation\u0026mdash;effects that combined with sepsis-related renal ischemia, exacerbate kidney dysfunction\u003csup\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e,\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e\u003c/sup\u003e; conversely, preexisting AKI impairs myoglobin and cytokine clearance, amplifying muscle necrosis and forming a vicious cycle\u003csup\u003e\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e\u003c/sup\u003e. Clinically, this comorbidity correlates with longer ICU stays (5.99 days in RM vs. 4.67 days in non-RM patients), highlighting the need for prioritized renal monitoring in RM patients. The RM group patients experienced more frequent invasive ventilation (83.61% vs. 55.27%) and CRRT (21.12% vs. 12.63%), indicating that RM might drive advanced organ support, showing the needs for integrated assessment of muscle injury and renal function in septic patients.\u003c/p\u003e\u003cp\u003eSeveral studies have focused on predicting outcomes in patients with RM\u003csup\u003e18,19\u003c/sup\u003e, however, there are few studies investigating the prediction of the occurrence of rhabdomyolysis. Traditional RM prediction relies on single biomarkers (e.g., CK) with limited early sensitivity, and no tailored risk stratification tools exist for septic populations\u003csup\u003e\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e\u003c/sup\u003e. To address this gap, we developed an interpretable machine learning model for RM prediction in ICU septic patients, with the XGBoost model emerging as the optimal approach. This model achieved an AUC of 0.924 (95% CI: 0.907\u0026ndash;0.941) and a Brier score of 0.90 in the testing set, outperforming logistic regression and other machine learning algorithms (e.g., random forest, ANN). DCA further confirmed its clinical utility, as it provided higher net benefits across a wide threshold probability range (0.1\u0026ndash;0.8) compared to \"treat all\" or \"treat none\" strategies\u0026mdash;critical for guiding targeted interventions and optimizing ICU resource allocation.\u003c/p\u003e\u003cp\u003eThe SHAP analysis identified CK-CKMB ratio, AST, and InvasiveVent as the top three predictors of RM-findings that supported by both pathophysiological mechanisms and existing literature. The CK-CKMB ratio stood out as the most influential predictor of RM. Notably, RM is clinically defined by an acute increase in serum CK to more than five times the upper normal limit, with myocardial infarction excluded based on a CK-MB fraction\u0026thinsp;\u0026lt;\u0026thinsp;5%\u003csup\u003e21\u003c/sup\u003e. Aligning with this diagnostic framework, our data showed a 4.8-fold higher ratio in RM versus non-RM patients (111 vs. 23 U/L, P\u0026thinsp;\u0026lt;\u0026thinsp;0.001), indicating that higher CK-CKMB ratio is associated with increased skeletal muscle injury. There is observational and experimental data demonstrating that AST can be elevated in patients with RM due to muscle release of these enzymes\u003csup\u003e\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e\u003c/sup\u003e, Liver failure was more common for intense RM patients\u003csup\u003e\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e\u003c/sup\u003e. In addition, sepsis could induce liver injury in any stage, and liver dysfunction is one of the hallmarks of the progressive development of sepsis into multi-organ dysfunction\u003csup\u003e\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e\u003c/sup\u003e. These studies could explain the elevation of AST in sepsis patients with RM. Notably, our study also found that elevated AST (117 vs. 40 U/L, P\u0026thinsp;\u0026lt;\u0026thinsp;0.001) serve as indirect markers of skeletal muscle damage. However, whether there is an interaction between the liver and skeletal muscle during the development of rhabdomyolysis requires further basic research to confirm. Diaphragm biopsy specimens obtained from mechanically ventilated patients exhibit significant inflammatory infiltration and sarcomeric disarray\u0026mdash;pathological features that closely resemble those observed in animal models of load-induced muscle injury\u003csup\u003e\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e,\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e\u003c/sup\u003e. Notably, high levels of respiratory effort are frequently documented in mechanically ventilated patients; this phenomenon is primarily driven by elevated respiratory drive, insufficient ventilator support, and episodes of patient\u0026ndash;ventilator dyssynchrony. Collectively, these factors suggest that critically ill patients undergoing mechanical ventilation are at substantial risk of developing load-induced diaphragm injury\u003csup\u003e\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e\u003c/sup\u003e. Similarly, our study showed that the proportion of patients requiring InvasiveVent was significantly higher in the RM group than in the non-RM group. However, whether InvasiveVent directly contributes to RM via ventilator-induced diaphragm injury or disuse atrophy requires further basic and clinical research to be validated. Interestingly, SHAP analysis showed the negative contribution of InvasiveVent to RM prediction, indicating that InvasiveVent itself may confer indirect benefits via improved organ perfusion.\u003c/p\u003e\u003cp\u003eThis study advances existing knowledge in three key ways. First, it is the first to develop an machine learning-based RM prediction model specifically for ICU septic patients, whereas previous studies focused on narrow subgroups such as trauma and drug-induced RM\u003csup\u003e28,29\u003c/sup\u003e. Our large sample size (3782 patients from the MIMIC database) and multi-method feature selection (univariate analysis, Lasso, Boruta) enhance the model\u0026rsquo;s robustness and generalizability. Second, the emphasis on model interpretability via SHAP addresses a major limitation of \"black-box\" machine learning models in clinical practice: we not only identified key predictors but also quantified their individual contributions (e.g., a CK-CKMB ratio of 111 U/L increases RM probability by ~\u0026thinsp;5%), facilitating clinician trust and adoption\u003csup\u003e\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e\u003c/sup\u003e. Third, the XGBoost model\u0026rsquo;s ability to capture non-linear interactions outperforms traditional linear models, which often fail to account for the complex crosstalk between inflammation and organ dysfunction in sepsis\u003csup\u003e\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e\u003cp\u003eThis study has several limitations. First, due to the lack of an independent external cohort, we only performed internal validation through training/testing set splitting. This may restrict the model\u0026rsquo;s generalizability to other ICU populations, such as those in European or Asian settings where sepsis management protocols differ\u003csup\u003e\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e,\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e\u003c/sup\u003e. Second, the retrospective design led to missing data on critical variables\u0026mdash;including myoglobin levels (a direct marker of RM) and sepsis etiology, such as whether infections were bacterial or viral. The inclusion of these variables could have potentially improved the model\u0026rsquo;s predictive performance. Third, the model was developed solely based on baseline admission data and did not incorporate dynamic changes in biomarkers (e.g., serial creatine kinase measurements) or clinical interventions like fluid resuscitation. Such dynamic information is critical for real-time assessment of rhabdomyolysis risk in clinical practice. Finally, we were unable to establish a causal relationship between certain predictors (e.g., InvasiveVent) and RM. This is because InvasiveVent may reflect the severity of sepsis rather than act as a direct cause of muscle injury.\u003c/p\u003e\u003cp\u003eIn conclusion, we developed a highly performant and interpretable XGBoost model to predict RM in ICU septic patients, using readily available clinical variables (CK-CKMB ratio, AST, InvasiveVent) that facilitate seamless clinical implementation. Future studies should focus on external validation in multi-center prospective cohorts, integrating dynamic biomarkers (e.g., serial myoglobin) to develop real-time prediction tools, and conducting randomized controlled trials to verify whether model-guided interventions reduce RM-related AKI and mortality. With further refinement, this model has the potential to become a standard tool for early RM risk stratification in septic patients, improving clinical decision-making and patient outcomes.\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003cdiv class=\"DefinitionList\"\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eAKI\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eAcute kidney injury\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eAMI\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eAcute myocardial infarction\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eANN\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eArtificial neural network\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eAUC\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eArea under the receiver operating characteristic curve\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eCHF\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eCongestive heart failure\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eCK\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eCreatine kinase\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eCKD\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eChronic kidney disease\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eCLF\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eChronic liver failure\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eCPR\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eCardiopulmonary resuscitation\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eCRF\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eChronic renal failure\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eCRRT\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eContinuous renal replacement therapy\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eICU\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eIntensive care unit\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eDCA\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eDecision curve analysis\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eDM\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eDermatomyositis\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eInvasiveVent\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eInvasive mechanical ventilation\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eLASSO\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eLeast absolute shrinkage and selection operator\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eMIMIC-IV\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eIntensive Care IV\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003ePM\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003ePolymyositis\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eRM\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eRhabdomyolysis\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eRRT\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eRenal replacement therapy\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eSE\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eStandard error\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eSHAP\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eShapley Additive Explanations\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eSOFA\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eSequential Organ Failure Assessment\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eSVM\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eSupport vector machine\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eXGBoost\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eExtreme gradient boosting\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003c/div\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eSubmission declaration and verification\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe work described has not been published previously, and is not under consideration for publication elsewhere.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthics approval and consent to participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis retrospective study utilized data from the publicly available MIMIC-IV database. The requirement for ethical approval and informed consent was\u0026nbsp;waived by the Institutional Review Board of Tianjin Medical University General Hospital. The study was conducted\u0026nbsp;in accordance with the Declaration of Helsinki. Access to the MIMIC-IV database was granted after completing the required Collaborative Institutional Training Initiative (CITI) course.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for publication\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAll the authors have consented to the publication of this research.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAvailability of data and materials\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.\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\n\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study was supported by the Science and Technology Commission of Chongqing (No.0202czzx2106), National Natural Science Foundation of China (No.82502660). \u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eClinical trial number\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthor contributions statement\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eDaqian Gu gave the study concept and design; Hongbin Deng drafted the manuscript; Xiangyi Zhou carried out the statistical analysis; Fachun Zhou supervised the study; all authors read and approved the final manuscript.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAcknowledgments\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNone.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eSinger M, Deutschman CS, Seymour CW, et al. The Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3). JAMA. 2016;315(8):801\u0026ndash;10.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTorres PA, Helmstetter JA, Kaye AM, Kaye AD. Rhabdomyolysis: pathogenesis, diagnosis, and treatment. Ochsner J. 2015;15(1):58\u0026ndash;69.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eRawson ES, Clarkson PM, Tarnopolsky MA. Perspectives on exertional rhabdomyolysis. Sports Med. 2017;47(Suppl 1):33\u0026ndash;49.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eRout P, Chippa V, Adigun R. Rhabdomyolysis. \u003cem\u003eStatPearls.\u003c/em\u003e Treasure Island (FL) ineligible companies. Disclosure: Venu Chippa declares no relevant financial relationships with ineligible companies. Disclosure: Rotimi Adigun declares no relevant financial relationships with ineligible companies.: StatPearls Publishing Copyright \u0026copy; 2025. StatPearls Publishing LLC.; 2025.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eNedel W, Deutschendorf C, Portela LVC. Sepsis-induced mitochondrial dysfunction: A narrative review. World J Crit Care Med. 2023;12(3):139.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHu D, Sheeja Prabhakaran H, Zhang Y-Y, Luo G, He W, Liou Y-C. Mitochondrial dysfunction in sepsis: mechanisms and therapeutic perspectives. Crit Care. 2024;28(1):292.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSun J, Zhang J, Tian J, et al. Mitochondria in sepsis-induced AKI. J Am Soc Nephrol. 2019;30(7):1151\u0026ndash;61.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTomašev N, Glorot X, Rae JW, et al. A clinically applicable approach to continuous prediction of future acute kidney injury. Nature. 2019;572(7767):116\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHenry KE, Hager DN, Pronovost PJ, Saria S. A targeted real-time early warning score (TREWScore) for septic shock. Sci Transl Med. 2015;7(299):ra299122\u0026ndash;299122.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eGoh KH, Wang L, Yeow AYK, et al. Artificial intelligence in sepsis early prediction and diagnosis using unstructured data in healthcare. Nat Commun. 2021;12(1):711.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eDesautels T, Calvert J, Hoffman J, et al. Prediction of sepsis in the intensive care unit with minimal electronic health record data: a machine learning approach. JMIR Med Inf. 2016;4(3):e5909.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHou N, Li M, He L, et al. Predicting 30-days mortality for MIMIC-III patients with sepsis-3: a machine learning approach using XGboost. J translational Med. 2020;18(1):462.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eZhang Y, Xu W, Yang P, Zhang A. Machine learning for the prediction of sepsis-related death: a systematic review and meta-analysis. BMC Med Inf Decis Mak. 2023;23(1):283.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWang Z, Wang Q, Chen J, Cai L. Rhabdomyolysis in intensive care unit\u0026mdash;distinctive clinical indicators and prognosis. BMC Anesthesiol. 2025;25(1):84.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMiyauchi H, Okubo K, Iida K, et al. Multiple site inflammation and acute kidney injury in crush syndrome. Front Pharmacol. 2024;15:1458997.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBellomo R, Kellum JA, Ronco C, et al. Acute kidney injury in sepsis. Intensive Care Med. 2017;43(6):816\u0026ndash;28.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eZhou X, Yang Y, Li P, Wang F, Zhang L, Fu P. Efficacy of haemoadsorption combined with continuous renal replacement therapy in patients with rhabdomyolysis and acute kidney injury: a retrospective study. Clin kidney J. 2025;18(2):sfae406.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLiu C, Liu X, Mao Z, et al. Interpretable machine learning model for early prediction of mortality in ICU patients with rhabdomyolysis. Med Sci Sports Exerc. 2021;53(9):1826\u0026ndash;34.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLiu C, Shi J, Wang F et al. Development and validation of an interpretable multi-task model to predict outcomes in patients with rhabdomyolysis: a multicenter retrospective cohort study. EClinicalMedicine 2025;87.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLippi G, Schena F, Ceriotti F. Diagnostic biomarkers of muscle injury and exertional rhabdomyolysis. Clin Chem Lab Med (CCLM). 2018;57(2):175\u0026ndash;82.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLane R, Phillips M. Rhabdomyolysis. In. Vol 327: British Medical Journal Publishing Group; 2003:115\u0026ndash;116.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLim AK. Abnormal liver function tests associated with severe rhabdomyolysis. World J Gastroenterol. 2020;26(10):1020.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMartinez T, Liaud-Laval G, Laitselart P, et al. Study of the relationship between liver function markers and traumatic rhabdomyolysis: a retrospective study of hemorrhagic patients admitted to intensive care unit in a level I trauma center. Anesth Analgesia. 2023;136(5):842\u0026ndash;51.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLiu Z, Yuan X, Huang Y et al. The role of interferon-induced proteins with tetratricopeptide repeats 1 and 2 in Sepsis-induced acute liver injury. Infect Drug Resist 2024:2337\u0026ndash;49.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eVan den Berg M, Hooijman PE, Beishuizen A, et al. Diaphragm atrophy and weakness in the absence of mitochondrial dysfunction in the critically ill. Am J Respir Crit Care Med. 2017;196(12):1544\u0026ndash;58.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eJaber S, Petrof BJ, Jung B, et al. Rapidly progressive diaphragmatic weakness and injury during mechanical ventilation in humans. Am J Respir Crit Care Med. 2011;183(3):364\u0026ndash;71.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSchreiber A, Bertoni M, Goligher EC. Avoiding respiratory and peripheral muscle injury during mechanical ventilation: diaphragm-protective ventilation and early mobilization. Crit Care Clin. 2018;34(3):357\u0026ndash;81.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTarazona V, Figueiredo S, Hamada S, et al. Admission serum myoglobin and the development of acute kidney injury after major trauma. Ann Intensiv Care. 2021;11(1):140.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eYamanaka T, Takemura K, Hayashida M, Suyama K, Urakami S, Miura Y. Cabozantinib-induced serum creatine kinase elevation and rhabdomyolysis: a retrospective case series. Cancer Chemother Pharmacol. 2023;92(3):235\u0026ndash;40.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHuang D, Gong L, Wei C, Wang X, Liang Z. An explainable machine learning-based model to predict intensive care unit admission among patients with community-acquired pneumonia and connective tissue disease. Respir Res. 2024;25(1):246.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLi X, Wu R, Zhao W, et al. Machine learning algorithm to predict mortality in critically ill patients with sepsis-associated acute kidney injury. Sci Rep. 2023;13(1):5223.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eGildea A, Mulvihill C, McFarlane E, Gray A, Singer M. Recognition, diagnosis, and early management of suspected sepsis: summary of updated NICE guidance. BMJ 2024;385.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMehta Y, Paul R, Rabbani R, Acharya SP, Withanaarachchi UK. Sepsis management in Southeast Asia: a review and clinical experience. J Clin Med. 2022;11(13):3635.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"},{"header":"Tables","content":"\u003cp\u003e\u003cstrong\u003eTable 1\u0026nbsp;\u003c/strong\u003eBaseline characteristics and comparison between RM and non-RM in MIMIC database\u003c/p\u003e\n\u003ctable border=\"0\" cellspacing=\"0\" cellpadding=\"0\" width=\"620\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eDemographic characteristics\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003eOverall n=3782\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003eNon-RM n=2873\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003eRM n=909\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003eP value\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"2\" style=\"width: 36.0709%;\"\u003e\n \u003cp\u003eDemographic information\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.9758%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eMale gender, n (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e2148 [56.80]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e1504 [52.35]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e644 [70.85]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eAge(yd)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e65.00 [55.00, 75.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e67.00 [57.00, 76.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e58.00 [49.00, 69.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eHeight (cm)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e170.00 [163.00, 178.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e168.00 [163.00, 175.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e173.00 [165.00, 178.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eWeight (kg)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e79.00 [67.00, 94.50]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e77.20 [65.50, 92.30]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e84.60 [71.90, 98.60]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eBMI (kg/m\u003csup\u003e2\u003c/sup\u003e)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e27.47 [23.73, 32.03]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e27.21 [23.44, 31.74]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e28.41 [24.93, 32.86]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eLos_hospital (d)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e16.76 [9.60, 27.80]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e17.96 [10.04, 29.28]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e13.61 [7.56, 22.71]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eLos_icu (d)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e4.91 [2.44, 10.23]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e4.67 [2.28, 9.84]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e5.99 [2.84, 11.70]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eSeverity of illness\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eAKI_score (median [IQR])\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e2.00 [2.00, 3.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e2.00 [2.00, 3.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e2.00 [2.00, 3.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e0.005\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eApsiii (median [IQR])\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e54.00 [42.00, 67.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e54.00 [43.00, 67.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e53.00 [40.00, 69.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e0.542\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eSAPSii (median [IQR])\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e41.00 [33.00, 50.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e41.00 [33.00, 49.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e40.00 [31.00, 51.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e0.266\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eSOFA (median [IQR])\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e7.00 [5.00, 11.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e7.00 [5.00, 10.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e8.00 [6.00, 12.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eGCS (median [IQR])\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e13.00 [9.00, 14.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e13.00 [10.00, 14.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e13.00 [9.00, 14.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e0.002\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eSIRS (median [IQR])\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e3.00 [2.00, 4.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e3.00 [2.00, 3.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e3.00 [3.00, 4.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eLODS (median [IQR])\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e6.00 [4.00, 8.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e6.00 [4.00, 8.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e6.00 [4.00, 8.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eCharlson (median [IQR])\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e5.00 [3.00, 7.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e6.00 [4.00, 7.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e3.00 [1.00, 6.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eMELD (median [IQR])\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e17.58 [10.00, 24.68]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e18.00 [11.00, 25.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e16.57 [10.00, 24.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e0.038\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eOASIS (median [IQR])\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e35.00 [30.00, 40.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e35.00 [29.00, 40.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e36.00 [31.00, 42.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eVital signs\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eTemperature (℃)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e37.39 [37.00, 37.94]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e37.28 [37.00, 37.83]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e37.70 [37.20, 38.28]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e0.002\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eHR (bpm)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e109.00 [96.00, 122.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e108.00 [96.00, 121.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e111.00 [98.00, 122.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e0.045\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eRR \u0026nbsp;(bpm)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e28.75 [25.00, 33.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e29.00 [25.00, 33.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e28.00 [24.00, 32.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eSBP (mmHg)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e144.00 [130.00, 158.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e143.00 [129.00, 157.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e146.00 [134.00, 162.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eDBP (mmHg)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e84.00 [73.00, 96.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e84.00 [73.00, 96.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e85.00 [76.00, 97.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eMBP (mmHg)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e99.75 [89.00, 112.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e99.00 [88.00, 111.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e103.00 [93.00, 116.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e0.542\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eLaboratory fndings\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eSpo2 (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e100.00 [100.00, 100.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e100.00 [100.00, 100.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e100.00 [100.00, 100.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e0.037\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eCalcium_free (mmol/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e1.13 [1.08, 1.19]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e1.13 [1.08, 1.19]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e1.14 [1.08, 1.20]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e0.007\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eWBC (K/uL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e12.70 [8.70, 17.80]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e12.30 [8.30, 17.60]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e13.50 [10.00, 18.40]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eHematocrit %\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e31.80 [28.20, 36.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e30.90 [27.70, 34.80]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e34.60 [31.10, 38.60]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eMCH (pg)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e30.50 [28.90, 31.90]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e30.40 [28.70, 31.80]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e30.70 [29.40, 32.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eMCV (fL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e93.00 [88.00, 97.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e93.00 [88.00, 98.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e92.00 [88.00, 96.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e0.005\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eMCHC (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e33.20 [32.00, 34.30]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e32.90 [31.90, 34.10]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e33.90 [32.70, 34.90]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eRDW (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e15.60 [14.30, 17.10]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e16.00 [14.60, 17.50]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e14.70 [13.70, 15.60]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003ePLT (K/uL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e189.00 [125.00, 258.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e190.00 [121.00, 261.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e188.00 [139.00, 248.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e0.451\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eRBC (m/uL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e3.48 [3.05, 3.98]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e3.37 [2.97, 3.85]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e3.80 [3.39, 4.26]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eAlb (g/dl)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e2.90 [2.60, 3.30]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e2.90 [2.50, 3.30]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e3.10 [2.70, 3.40]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eCreatinine (mg/dl)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e1.30 [0.90, 2.30]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e1.30 [0.80, 2.20]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e1.50 [1.00, 2.40]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eBUN (mg/dl)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e28.00 [17.00, 43.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e29.00 [18.00, 45.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e25.00 [16.00, 38.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eAniongap\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e16.00 [13.00, 19.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e16.00 [13.00, 18.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e17.00 [14.00, 20.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003ePT (seconds)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e15.30 [13.30, 19.10]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e15.50 [13.30, 19.50]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e14.90 [13.00, 17.90]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003ePTT (seconds)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e33.50 [28.70, 42.48]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e33.70 [28.90, 42.30]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e32.70 [28.30, 42.90]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e0.139\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eINR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e1.40 [1.20, 1.80]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e1.40 [1.20, 1.80]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e1.30 [1.20, 1.70]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eCK_CKMB_ratio (U/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e33.00 [14.00, 92.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e23.00 [11.00, 54.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e111.00 [57.00, 210.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eALT (U/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e33.00 [18.00, 75.75]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e29.00 [16.00, 60.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e58.00 [29.00, 161.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eAST (U/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e50.00 [27.00, 120.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e40.00 [24.00, 84.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e117.00 [54.00, 335.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eALP (U/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e88.00 [62.00, 133.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e95.00 [67.00, 142.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e66.00 [49.00, 95.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eBilirubin_total (mg/dl)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e0.80 [0.40, 1.70]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e0.80 [0.40, 1.80]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e0.70 [0.40, 1.40]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eLDH (U/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e308.00 [218.00, 477.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e277.00 [205.00, 408.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e453.00 [302.00, 702.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eChloride (mg/dl)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e106.00 [102.00, 110.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e105.00 [101.00, 110.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e108.00 [104.00, 112.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eGlucose (mg/dl)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e155.50 [121.00, 204.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e150.00 [119.00, 198.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e171.00 [132.00, 224.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eBicarbonate (g/dl)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e24.00 [21.00, 26.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e24.00 [21.00, 27.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e23.00 [21.00, 26.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eHb (g/dl)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e10.50 [9.20, 11.90]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e10.10 [8.90, 11.40]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e11.70 [10.40, 12.90]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eK (mEq/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e4.40 [4.00, 4.90]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e4.30 [4.00, 4.80]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e4.60 [4.10, 5.20]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eNa (mEq/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e140.00 [137.00, 143.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e139.00 [136.00, 142.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e141.00 [138.00, 144.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eMg (mg/dL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e2.20 [1.90, 2.40]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e2.20 [1.90, 2.40]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e2.20 [2.00, 2.50]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eCa(mg/dL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e8.40 [7.90, 8.80]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e8.40 [7.90, 8.90]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e8.30 [7.90, 8.70]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eP (mg/dL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e4.10 [3.30, 5.10]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e4.00 [3.20, 4.90]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e4.40 [3.50, 5.40]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eInput_24h_sum (ml)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e4964.50 [2649.00, 8077.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e4255.00 [2301.00, 7067.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e7327.00 [4617.00, 10827.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eOutput_24h_sum (ml)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e1860.00 [1050.00, 3033.75]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e1770.00 [994.00, 2810.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e2340.00 [1306.50, 3580.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eOutput_urine_sum (ml)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e1302.50 [743.50, 2050.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e1270.00 [729.00, 1975.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e1430.00 [830.00, 2240.00]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eComorbidity, n (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eSmoker (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e328 ( 8.67)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e252 ( 8.77)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e76 ( 8.36)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e0.752\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eAlcohol_abuse (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e59 ( 1.56)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e41 ( 1.43)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e18 ( 1.98)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e0.308\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eHypertension (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e1391 (36.78)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e1046 (36.41)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e345 (37.95)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e0.422\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eDiabetes (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e1204 (31.84)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e978 (34.04)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e226 (24.86)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eMyocardial_infarct (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e279 ( 7.38)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e224 ( 7.80)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e55 ( 6.05)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e0.092\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eCongestive_heart_failure (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e1230 (32.52)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e1026 (35.71)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e204 (22.44)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eMild_liver_disease (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e890 (23.53)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e697 (24.26)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e193 (21.23)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e0.067\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eSevere_liver_disease (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e472 (12.48)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e426 (14.83)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e46 ( 5.06)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eRenal_disease (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e1016 (26.86)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e856 (29.79)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e160 (17.60)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eChronic_pulmonary_disease (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e1059 (28.00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e836 (29.10)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e223 (24.53)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e0.009\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eCerebrovascular_disease (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e550 (14.54)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e405 (14.10)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e145 (15.95)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e0.184\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003ePeripheral_vascular_disease (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e504 (13.33)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e373 (12.98)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e131 (14.41)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e0.294\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eDementia (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e123 ( 3.25)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e105 ( 3.65)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e18 ( 1.98)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e0.018\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003ePeptic_ulcer_disease (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e162 ( 4.28)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e140 ( 4.87)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e22 ( 2.42)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e0.002\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eParaplegia (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e197 ( 5.21)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e146 ( 5.08)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e51 ( 5.61)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e0.589\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eMalignant_cancer (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e578 (15.28)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e509 (17.72)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e69 ( 7.59)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eMetastatic_solid_tumor (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e179 ( 4.73)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e151 ( 5.26)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e28 ( 3.08)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e0.009\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eAids (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e41 ( 1.08)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e30 ( 1.04)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e11 ( 1.21)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e0.812\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eRheumatic_disease (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e171 ( 4.52)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e144 ( 5.01)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp;27 ( 2.97)\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e0.013\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eAKI (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e3224 (85.25)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e2422 (84.30)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;802 (88.23)\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e0.004\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eTreatment status\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eInvasiveVent (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e2348 (62.08)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e1588 (55.27)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;760 (83.61)\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eCPR (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e76 ( 2.01)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e45 ( 1.57)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp;31 ( 3.41)\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eCRRT (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e555 (14.67)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e363 (12.63)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;192 (21.12)\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\n \u003cp\u003eRRT (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 22.0612%;\"\u003e\n \u003cp\u003e772 (20.41)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\n \u003cp\u003e544 (18.93)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\n \u003cp\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;228 (25.08)\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 28.9855%;\"\u003e\u003cbr\u003e\u003c/td\u003e\n \u003ctd style=\"width: 7.08535%;\"\u003e\u003cbr\u003e\u003c/td\u003e\n \u003ctd style=\"width: 14.9758%;\"\u003e\u003cbr\u003e\u003c/td\u003e\n \u003ctd style=\"width: 21.9002%;\"\u003e\u003cbr\u003e\u003c/td\u003e\n \u003ctd style=\"width: 18.0354%;\"\u003e\u003cbr\u003e\u003c/td\u003e\n \u003ctd style=\"width: 9.01771%;\"\u003e\u003cbr\u003e\u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cem\u003eData are shown as median with interquartile range (IQR) for continuous variables and number with percentage for categorical variables\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eSOFA: Sequential Organ Failure Assessment, SAPSII: Simplified Acute Physiology Score II, APSIII: Acute Physiology Score III, OASIS: Oxford Acute Severity of Illness Score, GCS: Glasgow Coma Scale, SIRS: Systemic Inflammatory Response Syndrome, LODS: Logistic Organ Dysfunction System, MELD: Model for End-Stage Liver Disease, Charlson: Charlson Comorbidity Index, RM: Rhabdomyolysis, BMI: Body Mass Index, HR: Heart Rate, RR: Respiratory Rate, SBP: Systolic Blood Pressure, DBP: Diastolic Blood Pressure, MBP: Mean Blood Pressure, SpO2: Oxygen Saturation, WBC: White Blood Cell, MCH: Mean Corpuscular Hemoglobin, MCV: Mean Corpuscular Volume, MCHC: Mean Corpuscular Hemoglobin Concentration, RDW: Red Cell Distribution Width, PLT: Platelet, RBC: Red Blood Cell, Alb: Albumin, BUN: Blood Urea Nitrogen, PT: Prothrombin Time, PTT: Partial Thromboplastin Time, INR: International Normalized Ratio, ALT: Alanine Aminotransferase, AST: Aspartate Aminotransferase, ALP: Alkaline Phosphatase, LDH: Lactate Dehydrogenase, Hb: Hemoglobin, AKI: Acute Kidney Injury, CPR: Cardiopulmonary Resuscitation, CRRT: Continuous Renal Replacement Therapy, RRT: Renal Replacement Therapy, IQR: Interquartile Range\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 2\u0026nbsp;\u003c/strong\u003ePerformance of 6 machine learning-based models for predicting ICU admission in the validation set\u003c/p\u003e\n\u003ctable border=\"0\" cellspacing=\"0\" cellpadding=\"0\" width=\"642\"\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 60px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eModel\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 49px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eAUC\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 62px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e95% CI Lower\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 62px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e95% CI Upper\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 42px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eAccuracy\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 42px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ePrecision\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 46px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eSensitivity\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 46px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eSpecificity\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 40px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eF1 Score\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 48px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eKappa\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 48px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eYouden\u0026apos;s J\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 49px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ePPV\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 49px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eNPV\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 60px;\"\u003e\n \u003cp\u003eLogistic\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 49px;\"\u003e\n \u003cp\u003e0.877\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 62px;\"\u003e\n \u003cp\u003e0.856\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 62px;\"\u003e\n \u003cp\u003e0.898\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 42px;\"\u003e\n \u003cp\u003e0.826\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 42px;\"\u003e\n \u003cp\u003e0.712\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 46px;\"\u003e\n \u003cp\u003e0.463\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 46px;\"\u003e\n \u003cp\u003e0.941\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 40px;\"\u003e\n \u003cp\u003e0.561\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 48px;\"\u003e\n \u003cp\u003e0.459\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 48px;\"\u003e\n \u003cp\u003e0.404\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 49px;\"\u003e\n \u003cp\u003e0.712\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 49px;\"\u003e\n \u003cp\u003e0.847\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 60px;\"\u003e\n \u003cp\u003eDecision Tree\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 49px;\"\u003e\n \u003cp\u003e0.886\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 62px;\"\u003e\n \u003cp\u003e0.864\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 62px;\"\u003e\n \u003cp\u003e0.907\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 42px;\"\u003e\n \u003cp\u003e0.853\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 42px;\"\u003e\n \u003cp\u003e0.709\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 46px;\"\u003e\n \u003cp\u003e0.662\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 46px;\"\u003e\n \u003cp\u003e0.914\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 40px;\"\u003e\n \u003cp\u003e0.684\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 48px;\"\u003e\n \u003cp\u003e0.589\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 48px;\"\u003e\n \u003cp\u003e0.576\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 49px;\"\u003e\n \u003cp\u003e0.709\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 49px;\"\u003e\n \u003cp\u003e0.895\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 60px;\"\u003e\n \u003cp\u003eRandom Forest\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 49px;\"\u003e\n \u003cp\u003e0.911\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 62px;\"\u003e\n \u003cp\u003e0.891\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 62px;\"\u003e\n \u003cp\u003e0.930\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 42px;\"\u003e\n \u003cp\u003e0.876\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 42px;\"\u003e\n \u003cp\u003e0.799\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 46px;\"\u003e\n \u003cp\u003e0.643\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 46px;\"\u003e\n \u003cp\u003e0.949\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 40px;\"\u003e\n \u003cp\u003e0.713\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 48px;\"\u003e\n \u003cp\u003e0.635\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 48px;\"\u003e\n \u003cp\u003e0.592\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 49px;\"\u003e\n \u003cp\u003e0.799\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 49px;\"\u003e\n \u003cp\u003e0.894\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 60px;\"\u003e\n \u003cp\u003eXGBoost\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 49px;\"\u003e\n \u003cp\u003e0.924\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 62px;\"\u003e\n \u003cp\u003e0.907\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 62px;\"\u003e\n \u003cp\u003e0.941\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 42px;\"\u003e\n \u003cp\u003e0.883\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 42px;\"\u003e\n \u003cp\u003e0.791\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 46px;\"\u003e\n \u003cp\u003e0.695\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 46px;\"\u003e\n \u003cp\u003e0.942\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 40px;\"\u003e\n \u003cp\u003e0.740\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 48px;\"\u003e\n \u003cp\u003e0.664\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 48px;\"\u003e\n \u003cp\u003e0.637\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 49px;\"\u003e\n \u003cp\u003e0.791\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 49px;\"\u003e\n \u003cp\u003e0.907\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 60px;\"\u003e\n \u003cp\u003eSVM\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 49px;\"\u003e\n \u003cp\u003e0.885\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 62px;\"\u003e\n \u003cp\u003e0.866\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 62px;\"\u003e\n \u003cp\u003e0.905\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 42px;\"\u003e\n \u003cp\u003e0.825\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 42px;\"\u003e\n \u003cp\u003e0.720\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 46px;\"\u003e\n \u003cp\u003e0.445\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 46px;\"\u003e\n \u003cp\u003e0.945\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 40px;\"\u003e\n \u003cp\u003e0.550\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 48px;\"\u003e\n \u003cp\u003e0.449\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 48px;\"\u003e\n \u003cp\u003e0.390\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 49px;\"\u003e\n \u003cp\u003e0.720\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 49px;\"\u003e\n \u003cp\u003e0.844\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 60px;\"\u003e\n \u003cp\u003eANN\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 49px;\"\u003e\n \u003cp\u003e0.911\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 62px;\"\u003e\n \u003cp\u003e0.893\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 62px;\"\u003e\n \u003cp\u003e0.929\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 42px;\"\u003e\n \u003cp\u003e0.865\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 42px;\"\u003e\n \u003cp\u003e0.772\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 46px;\"\u003e\n \u003cp\u003e0.621\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 46px;\"\u003e\n \u003cp\u003e0.942\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 40px;\"\u003e\n \u003cp\u003e0.688\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 48px;\"\u003e\n \u003cp\u003e0.603\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 48px;\"\u003e\n \u003cp\u003e0.563\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 49px;\"\u003e\n \u003cp\u003e0.772\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 49px;\"\u003e\n \u003cp\u003e0.887\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cem\u003eAUC: area under the receiver operating characteristic curve; XGBoost: eXtreme gradient boosting; SVM:\u0026nbsp;\u003c/em\u003e\u003cem\u003eSupport Vector Machine\u003c/em\u003e\u003cem\u003e; ANN:\u0026nbsp;\u003c/em\u003e\u003cem\u003eArtificial Neural Network\u003c/em\u003e\u003c/p\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":"Sepsis, Rhabdomyolysis, Machine Learning, Predictive Model, Intensive Care","lastPublishedDoi":"10.21203/rs.3.rs-7904814/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7904814/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e\u003cp\u003eSepsis is a common condition in the intensive care unit (ICU) and is frequently complicated by rhabdomyolysis, which can lead to serious consequences such as acute kidney injury. Currently, there is a lack of effective tools for the early prediction of sepsis-associated rhabdomyolysis.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e\u003cp\u003eThis retrospective study analyzed 3,782 sepsis patients from the MIMIC-IV database. Three feature selection methods (multivariate analysis, LASSO regression, and the Boruta algorithm) were used to identify predictors. Six machine learning models (logistic regression, decision tree, random forest, XGBoost, support vector machine, and artificial neural network) were developed to predict the occurrence of rhabdomyolysis.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e\u003cp\u003eTen predictive features were ultimately identified. The XGBoost model demonstrated the best performance, achieving an area under the receiver operating characteristic curve (AUC) of 0.924 (95% CI: 0.907\u0026ndash;0.941) in the validation set. SHAP analysis revealed that the CK/CKMB ratio, aspartate aminotransferase (AST), and invasive mechanical ventilation were the most important predictors.\u003c/p\u003e\u003ch2\u003eConclusions\u003c/h2\u003e\u003cp\u003eThe machine learning-based prediction model accurately identifies the risk of rhabdomyolysis in sepsis patients, facilitating the early recognition of high-risk individuals and enabling timely interventions.\u003c/p\u003e","manuscriptTitle":"A Machine Learning-Based Model for Predicting Rhabdomyolysis in Patients With Sepsis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-10 09:55:36","doi":"10.21203/rs.3.rs-7904814/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-01-27T05:45:48+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-26T22:46:37+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-17T03:54:42+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"161276788200925313880652658436460071768","date":"2025-12-13T07:27:36+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"275969491942321012181136171510910707141","date":"2025-12-09T15:08:34+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-12-05T10:43:25+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-11-10T05:25:32+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-11-05T10:12:47+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-11-05T10:10:17+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Medical Informatics and Decision Making","date":"2025-10-20T10:31:35+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":"9b13b594-bf1f-4b30-aba6-ef2055ebcb66","owner":[],"postedDate":"December 10th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-13T19:53:16+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-10 09:55:36","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7904814","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7904814","identity":"rs-7904814","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}