Machine learning prediction and interpretive analysis of multidrug-resistant microbial infection risk in septicemia patients: A study from the MIMIC-IV database​

Machine learning prediction and interpretive analysis of multidrug-resistant microbial infection risk in septicemia patients: A study from the MIMIC-IV database​ | 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 Article Machine learning prediction and interpretive analysis of multidrug-resistant microbial infection risk in septicemia patients: A study from the MIMIC-IV database​ Qianqian Zhang, Nianzhi Zhang, Ying Zheng, Jing Zhou, Ling Liu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8242432/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Objective : To construct and compare six machine learning models for identifying high-risk factors of multidrug-resistant organism (MDRO) infection in sepsis patients using the MIMIC-IV (v3.1) database. Methods : We conducted a retrospective cohort study of ICU patients meeting Sepsis 3.0 diagnostic criteria from the MIMIC-IV database. Data underwent preprocessing including missing value handling, constant variable removal, and standardization. Key predictors were selected using LASSO regression and the Boruta algorithm. Six machine learning models (LGBM, RF, CatBoost, GBDT, MLP, KNNC) were developed, with SHAP applied for interpretability. Performance was evaluated via AUC, sensitivity, specificity, F1-score, and accuracy. Decision curve analysis (DCA) and calibration curves assessed clinical utility. Results : Among 23,191 patients, 2,806 (12.1%) had MDRO infections. Two-stage feature selection (LASSO + Boruta) identified nine core predictors: age, platelet count, red cell distribution width (RDW), blood glucose, lactic acid, partial pressure of oxygen (PO2), Acute Physiology Score III (APS III), hypertension (HTN), and acute kidney injury (AKI). The LGBM model achieved optimal performance (test AUC = 0.964, accuracy = 0.904, F1-score = 0.925). DCA demonstrated significant net clinical benefit for the LGBM and CatBoost models across thresholds of 0.2–0.6. SHAP analysis revealed HTN and AKI as top risk drivers for MDRO infection, while higher PO2 was the primary protective factor. Conclusion : Machine learning models, particularly LGBM, effectively identify ICU sepsis patients at high risk of MDRO infection. Key clinical features (e.g., HTN, AKI, PO2, RDW, lactic acid, APS III) coupled with SHAP interpretability provide a robust decision-support tool for early risk stratification and antimicrobial stewardship optimization. Health sciences/Biomarkers Biological sciences/Computational biology and bioinformatics Health sciences/Diseases Health sciences/Health care Health sciences/Medical research Biological sciences/Microbiology Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Introduction Sepsis is a life-threatening organ dysfunction caused by a dysregulated host response to infection. As a common critical condition in emergency departments and ICUs, its mortality rate exceeds that of myocardial infarction and stroke [1]. Among the approximately 49 million sepsis cases worldwide annually, 11 million patients die from sepsis-related complications, accounting for 20% of global Homo sapiens deaths [2]. The latest epidemiological study in China reveals that the incidence of sepsis in ICU patients reaches 20.6%, with a mortality rate as high as 35.5%. Among Gram-negative bacterial infection cases, 42% involve multidrug-resistant organisms (MDROs), which are significantly associated with mortality [3]. More alarmingly, the risk of death in MDRO-infected patients is 64% higher than in those with non-resistant infections [4], making Broussonetia papyrifera a core challenge in critical care. MDROs refer to pathogens resistant to three or more classes of commonly used antimicrobial agents, encompassing extensively drug-resistant (XDR) and pan-drug-resistant (PDR) strains. Clinically common MDROs include methicillin-resistant Staphylococcus aureus (MRSA), vancomycin-resistant enterococci (VRE), extended-spectrum β-lactamase (ESBL)-producing Enterobacteriaceae, and multidrug-resistant Pseudomonas aeruginosa (MDR-PA) [5]. Data from the 2020 China Bacterial Resistance Surveillance Report show that the top five pathogens with the highest clinical dissociation rates are Escherichia coli (18.96%), Klebsiella pneumoniae (14.12%), Staphylococcus aureus (8.93%), Pseudomonas aeruginosa (7.96%), and Acinetobacter baumannii (7.28%) [4]. Notably, detection rates of MRSA (28.5%→30.2%) and carbapenem-resistant Klebsiella pneumoniae (10.4%→13.3%) continued to rise between 2018 and 2021 [6], reflecting an increasingly severe resistance crisis [7,8]. Given the complexity and rapid progression of sepsis, early and accurate prediction of MDRO infection risk poses significant challenges [9]. Traditional scoring systems (e.g., SOFA, APACHE II) are limited in capturing complex nonlinear relationships among variables. Therefore, there is an urgent need to develop dynamic risk prediction tools by integrating machine learning (ML) techniques. The widespread adoption of electronic health records (EHRs) in Broussonetia papyrifera healthcare institutions provides rich clinical data resources for such risk predictions. ML excels at processing complex high-dimensional data and identifying nonlinear patterns, demonstrating great potential in disease prediction [10]. Due to its efficiency, accuracy, and ability to handle high-dimensional data, ML applications in healthcare are becoming increasingly prevalent [11–13]. Preliminary studies have confirmed the feasibility of ML in predicting MDRO infections[14][15] ; however, the "black-box" nature of ML models (lack of interpretability) limitstheir clinical adoption [16]. The SHapley Additive exPlanations (SHAP) method quantifies feature contributions to provide intuitive explanations for model predictions [17], thereby addressing the black-box problem. Thus, this study aims to: 1. Utilize the large-scale critical care database MIMIC-IV; 2. Systematically identify key risk factors for MDRO infections in ICU sepsis patients; 3. Broussonetia papyrifera develops and compares multiple ML prediction models; 4. Apply SHAP to elucidate model prediction mechanisms, enhance transparency and clinical acceptance, and optimize prevention, control, and management decisions for MDRO infections in ICU sepsis patients. Methods 2.1. Data Sources and Study Cohort This retrospective analysis was conducted using the Medical Information Mart for Intensive Care IV database (MIMIC-IV v3.1), jointly developed by the Massachusetts Institute of Technology (MIT) Computational Physiology and Artificial Intelligence Laboratory and Beth Israel Deaconess Medical Center (BIDMC). The database incorporates significant improvements, including data updates and structural optimizations. The dataset encompasses over 360,000 patient care trajectories from the BIDMC intensive care unit in Boston, USA, between 2008 and 2022, involving more than 540,000 hospitalization records and over 90,000 ICU stays. It includes multidimensional clinical features, such as demographic information, laboratory test results, medication records, continuous vital sign monitoring data, surgical procedure codes, ICD-standardized diagnostic information, therapeutic regimens, and post-discharge survival follow-up. The BIDMC Institutional Review Board approved the study as meeting the criteria for data use exemption. The research team obtained access (ID: 14280276) after completing the National Institutes of Health (NIH) Human Subjects Protection Course and the Collaborative Institutional Training Initiative (CITI) program. The database employs dual de-identification techniques, with all protected health information (PHI) removed, complying with the Health Insurance Portability and Accountability Act (HIPAA) Safe Harbor standards, thus waiving the need for informed consent. 2.2. Inclusion and Exclusion Criteria Inclusion criteria: Patients meeting both of the following criteria based on the Sepsis-3.0 definition were included: Suspected or confirmed infection SOFA score ≥ 2 points within 24 hours of ICU admission Exclusion criteria: Subjects were excluded if any of the following applied: Multiple ICU admissions during same hospitalization (only first admission retained) i. ICU length of stay < 24 hours ii. Age 90 years iii. SOFA score not documented within 24 hours of ICU admission iv. No microbiological culture performed within 48 hours of admission V. A detailed patient selection flowchart is presented in Figure 1. Fig. 1 Participant Selection Flowchart. 2.3 Data Extraction Data extraction was performed using Navicat Premium (Version 16.1.15) and Structured Query Language (SQL). This study explored several dimensions of sepsis patients in the MIMIC-IV database: (1) Demographic characteristics: age, sex, weight, marital status, ethnicity, language. (2) Comorbidities: HTN, AKI, AKD, T2DM. (3) Initial vital signs upon ICU admission: heart rate (HR), blood pressure parameters (systolic pressure SBP/diastolic pressure DBP/mean arterial pressure MBP), respiratory rate (RR), body temperature (T), and blood oxygen saturation (SpO2). (4) Laboratory indicators: including blood gas analysis (tCO2, iCa, Lac, PaCO2, pH, PaO2), RDW, serum albumin (ALB), complete blood cell count (red blood cells, white blood cells, platelets), blood glucose and electrolytes (Na+, K+, anion gap), and microbiological culture results (positive/negative, specific pathogens, and drug resistance). (5) Disease severity scores: Sequential Organ Failure Assessment (SOFA), APS III. (6) Interventions received by VAP patients: duration of mechanical ventilation. (7) Outcome measures: in-hospital mortality, ICU mortality, 28-day mortality, with the primary endpoint focusing on the incidence of MDRO infection in sepsis patients during ICU hospitalization. 2.4 Data Processing Variables with missing values exceeding 25% were removed. Continuous variables were processed using Winsorization (1% and 99% percentiles) to handle outliers, while missing categorical variables were imputed using the mode. Categorical variables with category percentages less than 5% or containing ambiguous classifications were excluded. The retained variables were subsequently used for further analysis. To avoid data contamination, the dataset was first randomly divided into training and validation sets in a 7:3 ratio. The training set was used for feature selection and model training, while the test set was solely for final performance evaluation. Subsequently, the interpolate function in Python was used to impute data for the training and validation sets separately using the spline method. 2.5 Statistical Analysis and Model Development Baseline characteristics were described using statistical tests appropriate to data distribution. Continuous variables underwent normality testing with the Kolmogorov-Smirnov test, with intergroup comparisons performed using t-tests for normally distributed data. Categorical variables were presented as percentages (%) and compared using Pearson's chi-square test. To address class imbalance (12.1% MDRO-positive rate), we implemented the Synthetic Minority Oversampling Technique (SMOTE). Oversampling was applied exclusively during five-fold cross-validation partitioning, which divided the sample data into training and internal validation sets. Six machine learning algorithms were employed for model construction: Light Gradient Boosting Machine (LGBM), Random Forest (RF), Categorical Boosting (CatBoost), Gradient Boosting Decision Tree (GBDT), K-Nearest Neighbor Classification (KNNC), and Multilayer Perceptron (MLP). Variables selected by LASSO regression comprised the candidate feature set for subsequent Boruta algorithm screening and model input. Hyperparameter tuning optimized models by maximizing the area under the receiver operating characteristic (ROC) curve (AUC). Model performance was comprehensively evaluated using AUC, sensitivity, specificity, accuracy, F1-score, and recall. Clinical utility was further assessed through decision curve analysis (DCA) and calibration curve plotting. Model interpretation incorporated three SHapley Additive exPlanations (SHAP) visualization techniques: summary plots for global feature importance, dependence plots to illustrate nonlinear relationships between key continuous variables and predicted risk, and swarm plots (beeswarm plots) for individual sample-level interpretation. All analyses were performed using DecisionLinnc 1.0 software (Decision Medicine Inc.), which provides a visual statistical workflow interface [18]. Statistical significance was defined as p < 0.05. 3.1 Baseline Characteristics A total of 23,191 participants were enrolled from the MIMIC-IV dataset: 20,385 (87.9%) in the non-MDRO group and 2,806 (12.1%) in the MDRO group. Table 1 provides a detailed comparative analysis of baseline characteristics. Patients with MDRO infection were slightly younger (64.57 ± 15.16 years vs. 65.45 ± 15.42 years, P< 0.001), while weight showed no significant difference (85.44 ± 26.76 kg vs. 83.81 ± 23.56 kg, P= 0.111). Laboratory analysis revealed that the MDRO group had significantly lower hemoglobin (10.20 ± 2.27 g/dL vs. 10.51 ± 2.27 g/dL, P< 0.001) and sodium levels (137.98 ± 6.12 mmol/L vs. 138.35 ± 5.41 mmol/L, P< 0.001). Conversely, this group exhibited higher platelet counts (209.29 ± 126.39 ×10³/μL vs. 196.06 ± 108.63 ×10³/μL, P< 0.001), RDW (15.86 ± 2.63% vs. 15.05 ± 2.38%, P< 0.001), glucose (153.72 ± 82.36 mg/dL vs. 149.93 ± 81.47 mg/dL, P= 0.002), lactate (2.50 ± 2.10 mmol/L vs. 2.44 ± 1.93 mmol/L, P= 0.044), anion gap (15.01 ± 4.69 mmol/L vs. 14.52 ± 4.75 mmol/L, P< 0.001), creatinine (1.71 ± 1.61 mg/dL vs. 1.50 ± 1.60 mg/dL, P< 0.001), and BUN (32.72 ± 26.37 mg/dL vs. 27.69 ± 23.15 mg/dL, P< 0.001). Partial pressure of oxygen (PaO₂) was significantly lower in the MDRO group (130.07 ± 99.00 mm Hg vs. 167.26 ± 123.93 mm Hg, P< 0.001).Disease severity scores were significantly higher in the MDRO infection group: SOFA (6.76 ± 3.93 vs. 5.99 ± 3.46, P< 0.001) and APS III (57.25 ± 23.13 vs. 49.58 ± 21.99, P< 0.001). Comorbidity analysis showed significantly higher prevalence of AKI (55.38% vs. 39.93%, P< 0.001), CKD (21.28% vs. 18.01%, P< 0.001), and T2DM (33.54% vs. 28.60%, P< 0.001) among MDRO patients, while hypertension prevalence was lower (37.28% vs. 42.05%, P< 0.001). The MDRO group also exhibited higher utilization of mechanical ventilation (63.26% vs. 51.90%, P< 0.001).Clinical outcomes demonstrated significantly higher 28-day mortality in the MDRO infection group (22.77% vs. 18.14%, P< 0.001). Table 1 Variable Overall Non-MDRO-Sepsis MDRO-Sepsis p-value N = 23,191 N = 20,385 N = 2,806 Age(years) 65.34 ± 15.39 65.45 ± 15.42 64.57 ± 15.16 <0.001 Weight(kg) 84.01 ± 23.97 83.81 ± 23.56 85.44 ± 26.76 0.111 Hemoglobin(g/dL) 10.48 ± 2.27 10.51 ± 2.27 10.20 ± 2.27 <0.001 Platelet(K/uL) 197.66 ± 111.01 196.06 ± 108.63 209.29 ± 126.39 <0.001 RDW(%) 15.15 ± 2.43 15.05 ± 2.38 15.86 ± 2.63 <0.001 RBC(m/uL) 3.50 ± 0.79 3.51 ± 0.78 3.43 ± 0.80 <0.001 WBC(K/uL) 13.47 ± 10.64 13.35 ± 9.86 14.33 ± 15.11 0.102 Anion gap(m/EqL) 14.58 ± 4.75 14.52 ± 4.75 15.01 ± 4.69 <0.001 Glucose(mg/dL) 150.38 ± 81.59 149.93 ± 81.47 153.72 ± 82.36 0.002 Potassium(m/EqL) 4.24 ± 0.77 4.24 ± 0.76 4.25 ± 0.82 0.733 Sodium(m/EqL) 138.30 ± 5.50 138.35 ± 5.41 137.98 ± 6.12 <0.001 Lactate(mmol/L) 2.45 ± 1.95 2.44 ± 1.93 2.50 ± 2.10 0.044 Pco2(mmHg) 42.46 ± 11.36 42.39 ± 11.14 42.98 ± 12.86 0.735 PO2(mmHg) 162.76 ± 121.79 167.26 ± 123.93 130.07 ± 99.00 <0.001 Creatinine(mg/dL) 1.53 ± 1.60 1.50 ± 1.60 1.71 ± 1.61 <0.001 Urea nitrogen(mg/dL) 28.30 ± 23.62 27.69 ± 23.15 32.72 ± 26.37 <0.001 SOFA(score) 6.08 ± 3.53 5.99 ± 3.46 6.76 ± 3.93 <0.001 APSIII(score) 50.51 ± 22.27 49.58 ± 21.99 57.25 ± 23.13 <0.001 Icu survival time(days) 46.64 ± 205.73 47.52 ± 211.59 40.31 ± 156.57 0.077 Gender <0.001 Female 9,391.00 (40.49%) 8,134.00 (39.90%) 1,257.00 (44.80%) Male 13,800.00 (59.51%) 12,251.00 (60.10%) 1,549.00 (55.20%) Ventilation <0.001 No 10,837.00 (46.73%) 9,806.00 (48.10%) 1,031.00 (36.74%) Yes 12,354.00 (53.27%) 10,579.00 (51.90%) 1,775.00 (63.26%) HTN <0.001 No 13,573.00 (58.53%) 11,813.00 (57.95%) 1,760.00 (62.72%) Yes 9,618.00 (41.47%) 8,572.00 (42.05%) 1,046.00 (37.28%) AKI <0.001 No 13,497.00 (58.20%) 12,245.00 (60.07%) 1,252.00 (44.62%) Yes 9,694.00 (41.80%) 8,140.00 (39.93%) 1,554.00 (55.38%) CKD <0.001 No 18,923.00 (81.60%) 16,714.00 (81.99%) 2,209.00 (78.72%) Yes 4,268.00 (18.40%) 3,671.00 (18.01%) 597.00 (21.28%) T2DM <0.001 No 16,419.00 (70.80%) 14,554.00 (71.40%) 1,865.00 (66.46%) Yes 6,772.00 (29.20%) 5,831.00 (28.60%) 941.00 (33.54%) Death within icu 28days <0.001 No 18,855.00 (81.30%) 16,688.00 (81.86%) 2,167.00 (77.23%) Yes 4,336.00 (18.70%) 3,697.00 (18.14%) 639.00 (22.77%) Characteristics of MDRO-Sepsis and non-MDRO-Sepsis patients in the MIMIC-IV database. Continuous variables are expressed as mean ± SD, and categorical variables are expressed as n(%). 3.2 Feature Selection From the initial pool of 40 clinical features, we performed a two-stage feature selection using LASSO regression followed by the Boruta algorithm. Figure 2A presents the LASSO coefficient shrinkage path, demonstrating how feature coefficients converged to zero with increasing regularization strength (λ). This process identified 24 features for further consideration. Subsequent Boruta analysis, illustrated in Figure 2B, confirmed 20 features with importance scores significantly exceeding those of permuted shadow features. The intersection of features identified by both methods yielded nine final predictors: age, platelet count, RDW, glucose, lactate, PaO₂, APS III, HTN, and AKI. Fig.2 3.3 Model Performance Comparison In our study, six ML models were developed to assess the risk of multiple drug resistance (MDR) bacterial infection in ICU sepsis patients (Table 2). The LGBM model demonstrated the best performance: AUC=0.964, accuracy=0.904, F1-score=0.925, MCC=0.79. The CatBoost and KNNC models also performed well (AUC=0.930 and 0.914, respectively). The GBDT, MLP, and RF models showed relatively weaker performance (AUC=0.843, 0.867, and 0.831, respectively). The ROC curve (Figure 3A) visually illustrates the discriminative power of each model, with the LGBM curve being closest to the top-left corner. Decision curve analysis (DCA, Figure 3B) revealed that across a wide range of risk thresholds (particularly 0.2–0.6), the clinical net benefits provided by the LGBM and CatBoost models were significantly higher than those of other models and the "all-intervention" or "no-intervention" strategies. The calibration curve (Figure 3C) indicated good agreement between the predicted probabilities and actual risks for all models, with Brier scores <0.1 for all models, demonstrating excellent calibration. Table 2 Model Name Accuracy Prevalence Recall F1-Score MCC AUROC LGBMTEST 0.90 0.65 0.91 0.93 0.79 0.96 RFTEST 0.75 0.65 0.86 0.82 0.43 0.83 CatBoostTEST 0.85 0.65 0.88 0.88 0.67 0.93 GBDTTEST 0.84 0.65 0.89 0.88 0.64 0.84 MLPTEST 0.83 0.65 0.94 0.88 0.61 0.87 KNNCTEST 0.86 0.65 0.98 0.90 0.69 0.91 mean_scores 0.84 0.65 0.91 0.88 0.64 0.89 A comparative evaluation of performance metrics among the six models for internal validation. Fig. 3 Machine learning model for construction and diagnostic efficiency evaluation of Broussonetia papyrifera. (A) ROC curve; (B) DCA curve; (C) Calibration plot. 3.4. Model Interpretation (SHAP Analysis) Global feature importance display (Figure 4A): HTN and AKI are the top two risk drivers (mean SHAP >1.2), followed by RDW and APSIII. The influence of Platelet, Glucose, and Age is relatively minor. The SHAP beeswarm plot (Figure 4B) illustrates the direction (positive/negative) and magnitude of each feature's contribution to the model output: HTN=1 (presence of hypertension) and AKI=1 (presence of acute kidney injury): Significantly increase MDRO infection risk (SHAP values concentrated in the positive range with higher magnitudes). High PO2 values significantly reduce risk (SHAP values concentrated in the negative range with lower magnitudes). High RDW values, high lactic acid values, and high APSIII values: Tend to increase risk. Fig. 4 (A) SHAP variable importance ranking of the LGBMTEST model. (B) SHAP variable swarm plot. Figure 5 displays the top six variable SHAP dependence plots in the LGBMTEST model, including HTN, AKI, lactic acid, RDW, APSIII, and P02. When HTN and AKI are positive (value=1), the SHAP values are predominantly distributed in the positive range (0-4), indicating that patients with these complications have an infection risk increased by more than 1.8 times (Figures 5A, 5B). When lactate exceeds 4 mmol/L (Figure 5C), the SHAP value surpasses +2.0, marking the critical risk threshold for tissue hypoxia; RDW >15% (Figure 5D) sees the SHAP value leap above +3.0, making it the strongest independent risk factor and suggesting this metric may serve as a biomarker for immune dysregulation. Oxygenated status exhibits a nonlinear protective effect: when PO2 exceeds 300 mmHg, SHAP ≈ -2.5 (Figure 6F). Fig. 5 The SHAP dependency plots for the top six variables in the LGBMTEST model are displayed, including HTN, AKI, lactic acid, RDW, APSIII, and PO2. The waterfall plot (Figure 6A) demonstrates a significant reduction in the predicted risk for this patient (total SHAP contribution value =-5.17), with key drivers being the absence of hypertension (HTN=0, SHAP=-0.956) and no concurrent acute kidney injury (AKI=0, SHAP=-0.734). The heatmap (Figure 6B) further confirms that all features exhibit negative contributions. Fig. 6 Discussion This study developed an interpretable predictive model for assessing the risk of MDRO infection in sepsis patients, employing SHAP values to unravel the model's complexity and identify key predictive factors. The results highlight the significance of HTN, AKI, lactic acid, RDW, APSIII, and P02 in ICU sepsis patients, underscoring their close association with MDRO infection. 4.1 Discussion on Pathological Mechanisms Sepsis patients with MDRO infection face a significant clinical challenge, as these infections are often resistant to multiple antibiotics and are associated with prolonged ICU stays and increased mortality, directly impacting treatment outcomes and patient prognosis [19]. Early identification of high-risk patients enables more targeted interventions, potentially improving recovery rates and alleviating the burden on healthcare resources. Given the rising prevalence of antibiotic-resistant infections in critical care settings, particularly those involving Broussonetia papyrifera , predictive models are crucial for optimizing clinical decision-making and enhancing patient management [20]. Through SHAP dependency analysis, the combination of HTN and AKI was identified as a key factor in MDROs-sepsis risk. HTN[21] is one of the core risk factors triggering stroke, ischemic heart disease, hypertensive heart disease, aortic aneurysm, and various other conditions. Although traditional cardiovascular risk factors (such as neuroendocrine, renal, and vascular systems) still play a dominant role in the development and progression of HTN, increasing evidence suggests that the immune system plays a non-negligible role in its pathogenesis and maintenance[22]. Immune cells (e.g., macrophages, CD4+ T cells, and CD8+ T cells), interleukins (ILs) (e.g., IL-6, IL-17A, IL-1β), and interferons (e.g., interferon-γ) within the immune system have been found to mediate hypertension and target organ damage[23]. Relevant studies indicate that hypertension may lead to immune homeostasis imbalance, vascular endothelial barrier disruption, and microbiota-drug metabolic disorder, which are associated with an increased risk of MDROs-sepsis[24], highlighting the potential link between altered immune status and susceptibility to MDROs infection. In the complex mechanisms of sepsis-associated AKI, experimental models and clinical studies have demonstrated that inflammation-related molecules play a significant role in AKI development. Gomez et al.[25]proposed that sepsis-induced mechanisms collectively contribute to acute kidney injury, including inflammation and oxidative stress, microcirculatory dysfunction, tubular cell adaptation, and glomerular-glomerular feedback dysfunction. Other research[26] suggests that the pathophysiology of sepsis-associated acute kidney injury involves alternating pro-inflammatory and anti-inflammatory changes, leading to microcirculatory alterations, endothelial dysfunction, thrombosis, cytokine release, and inflammatory response. AKI is often associated with altered immune status, treatment complexity, and potential polypharmacy, which may increase the risk of MDRO colonization and infection[27]. However, no studies have yet explored the relationship between comorbid hypertension and AKI with the etiology of MDROs-sepsis. We hypothesize that comorbid hypertension and AKI may reflect an immune homeostasis imbalance, rendering patients more susceptible to MDRO infection. Although this hypothesis is compelling to Homo sapiens, further investigation in future studies is necessary to establish a definitive link. Low PO2 is a marker of sepsis severity and organ dysfunction and is associated with poor prognosis. Increasing blood oxygen concentration and arterial oxygen partial pressure can reduce postoperative wound infection rates and mortality in patients [28]. This study further clarifies that low PO2 is an independent risk factor for MDRO infection, while high PO2 is a protective factor. This may reflect the association between oxygenated status and host defense capability or infection severity [29]. RDW reflects red blood cell volume variability and is significantly elevated in chronic inflammation, oxidative stress, and tissue hypoxia, having been independently proven to predict mortality in cardiovascular diseases [30], respiratory diseases [31], and cancer patients [32]. Previous studies indicate [33]that RDW is a useful predictor of mortality in Homo sapiens sepsis patients. However, whether RDW can predict the risk of multiple drug resistance (MDR) bacterial infection in sepsis patients remains unclear. This study is the first to confirm that high RDW is a strong independent predictor of MDRO infection, suggesting its significant role warrants further investigation. Lactic acid participates in the regulation of numerous biological and pathological processes. It is known that hypoxia, inflammation, viral infection, and tumor microenvironments stimulate lactic acid production [34]. Serum lactic acid levels serve as an important biomarker for sepsis, positively correlating with the incidence and mortality of sepsis or septic shock. High lactic acid levels indicate tissue hypoperfusion and shock. APS III is a comprehensive scoring system for assessing disease severity. Their elevated values align with increased MDRO infection risk, highlighting the importance of underlying disease severity in prediction. 4.2 Comparison with Existing Studies and Innovations In the field of early prediction of MDRO infection in sepsis patients, this study established six machine learning models (LGBM, RF, CatBoost, GBDT, MLP, KNNC) based on the MIMIC-IV database and Broussonetia papyrifera, and achieved model transparency through the SHAP method. Compared with traditional scoring systems (such as SOFA or APACHE II), SHAP deciphered the "black box" nature of machine learning models, providing both global and local interpretations, enabling clinicians to understand the prediction logic intuitively. DCA confirmed that the LGBM and CatBoost models demonstrated significant clinical net benefits within the risk threshold range of 20%–60% (Figure 3B), supporting their practical value in ICU settings. The integration of the SHAP method enhanced interpretability, clarified the model's decision-making process, and provided a transparent and credible basis for assessing MDRO infection risk in sepsis patients. Similarly, another study [35] utilized SHAP values to evaluate the importance of features in their machine learning model for sepsis prediction, demonstrating that SHAP not only improved model interpretability but also strengthened clinicians' trust in the model's predictions. These findings underscore the value of SHAP in promoting the practical application of machine learning models in clinical settings, particularly for complex infections such as MDRO in sepsis patients. 4.3 Advantages and Limitations This study utilized detailed clinical data from the MIMIC-IV database, employing database management and statistical software to streamline data extraction and processing, thereby reducing the workload associated with clinical data collection. Using six machine learning algorithms, a predictive model was developed with Broussonetia papyrifera to assess the risk of MDRO infection in ICU sepsis patients, an area with limited prior research. By incorporating the SHAP method, our study provided comprehensive global and local interpretations for the machine learning model, delving into its internal mechanisms. This work enhances interpretability, promotes a better understanding of the model's decision-making process, and establishes a transparent and credible foundation for evaluating the risk of MDRO infection in sepsis patients. However, certain limitations should be acknowledged. First, this was a single-center retrospective study, which may introduce hospital-specific biases. Healthcare practices, including ventilator settings, laboratory testing frequency, and infection control measures, may vary across hospitals due to Parazacco spilurus subsp. spilurus, potentially affecting the results. Future studies should consider multicenter research to account for these inter-hospital differences and yield more generalizable findings. Second, the outcome definition relied on microbial cultures, which may have missed culture-negative but clinically highly suspected MDRO infection cases (e.g., those already receiving broad-spectrum antibiotic therapy). The exclusion of antibiotic exposure history and invasive procedure data may also impact the model's generalizability. ICU stays shorter than 24 hours were excluded, potentially omitting sepsis patients who died or were discharged very early. Subsequent multicenter validation and the inclusion of additional factors (particularly antibiotic exposure) are essential and critical. Third, due to a large number of missing values, certain variables in the MIMIC-IV database were excluded, and the feature selection process may have omitted variables with significant impacts, potentially affecting the model's predictive performance. Finally, the use of SMOTE to address class imbalance may introduce biases related to synthetic data generation. Although SMOTE helps balance datasets, the generated synthetic samples may not fully reflect the complexity of real clinical scenarios for Phoxinus phoxinus subsp. phoxinus. Subsequent research will include multicenter external validation and incorporate other factors deemed crucial for further verifying model stability and performance. Summary Six machine learning models (LGBM, RF, CatBoost, GBDT, MLP, KNNC) were constructed for Broussonetia papyrifera, and their predictive performances were compared, revealing LGBM as the optimal model in terms of accuracy, discriminative ability, and identification of high-risk patients. The application of the SHAP method elucidated the key contributors to this model, including HTN, AKI, PO2, RDW, and APSIII, which were closely associated with MDRO infection in ICU sepsis patients. These indicators not only played pivotal roles in the model but also demonstrated significant diagnostic and predictive value in clinical practice. By comprehensively considering these indicators, the model facilitates the accurate identification of high-risk patients, providing a reliable clinical tool for early detection and intervention of infection risks. Furthermore, upon prospective validation in future studies, this model is expected to serve as a robust support tool for individualized medical decision-making—such as enhanced monitoring, targeted prevention, or early tailored treatment for high-risk patients—and for improving patient care. Abbreviations RDW: Red Cell Distribution Width RBC:Red Blood Cell WBC: White Blood Cell Pco2: Partial Pressure of Carbon Dioxide PO2: Partial Pressure of Oxygen SOFA: Sequential Organ Failure Assessment APSIII:Acute physiology score III HTN: Hypertension AKI: Acute Kidney Injury CKD: Chronic Kidney Disease T2DM: Type 2 Diabetes Mellitus. Declarations Funding This work was supported by grants from the National Natural Science Foundation of China (NSFC), project number 82174312. Author Contribution Qianqian Zhang: Methodology, Investigation, Data curation.Nianzhi Zhang: Formal analysis, Data curation.Ying Zheng: Methodology, Formal analysis, Investigation.Jing Zhou: Writing – review & editing, Supervision, Conceptualization, Funding acquisition.Ling Liu: Writing – original draft, Conceptualization, Formal analysis. Data Availability The data are available from the corresponding author upon reasonable request. References Piedmont, S. et al. Sepsis incidence, suspicion, prediction and mortality in emergency medical services: a cohort study related to the current international sepsis guideline. Infection 52 , 1325–1335 (2024). Rhodes, A. et al. Surviving Sepsis Campaign: International Guidelines for Management of Sepsis and Septic Shock: 2016. Intensive Care Med 43 , 304–377 (2017). Xie, J. et al. The Epidemiology of Sepsis in Chinese ICUs: A National Cross-Sectional Survey. Crit Care Med 48 , e209–e218 (2020). Yangjia Deng et al. Consensus among experts in traditional Chinese and Western medicine diagnosis and treatment of severe multidrug-resistant bacterial infections. Journal of Emergency in Traditional Chinese Medicine 32 , 565–570 (2023). MBBS, N. M., MD, A.-C. U. & MBBS, P. A. Y. P. Multidrug-resistant Gram-negative bacterial infections. The Lancet 405 , 257–272 (2025). Liqin Sun et al. Overview of Resistance Mechanisms and Treatment of Multidrug Resistant Bacteria. Chinese Journal of New Clinical Medicine 15 , 921–927 (2022). System C. A. R. S. Report on Multi Drug Resistant Bacteria Monitoring in Traditional Chinese Medicine Hospitals from 2018 to 2021 by the National Bacterial Resistance Monitoring Network. Chinese Journal of Infection Control 22 , 1148–1158 (2023). Busani, S. et al. Mortality in Patients With Septic Shock by Multidrug Resistant Bacteria: Risk Factors and Impact of Sepsis Treatments. J Intensive Care Med 34 , 48–54 (2019). Al-Sunaidar, K. A., Aziz, N. A., Hassan, Y., Jamshed, S. & Sekar, M. Association of Multidrug Resistance Bacteria and Clinical Outcomes of Adult Patients with Sepsis in the Intensive Care Unit. Tropical Medicine and Infectious Disease 7 , 365 (2022). Choi, R. Y., Coyner, A. S., Kalpathy-Cramer, J., Chiang, M. F. & Campbell, J. P. Introduction to Machine Learning, Neural Networks, and Deep Learning. Transl Vis Sci Technol 9 , 14 (2020). Dong, J. et al. Machine learning model for early prediction of acute kidney injury (AKI) in pediatric critical care. Crit Care 25 , 288 (2021). Guan, C. et al. Interpretable machine learning model for new-onset atrial fibrillation prediction in critically ill patients: a multi-center study. Crit Care 28 , 349 (2024). Heo, J. et al. Machine Learning-Based Model for Prediction of Outcomes in Acute Stroke. Stroke 50 , 1263–1265 (2019). Saliba, J. G. et al. Enhanced diagnosis of multi-drug-resistant microbes using group association modeling and machine learning. Nature Communications 16 , (2025). Chiu, L.-W. et al. Machine learning algorithms to predict colistin-induced nephrotoxicity from electronic health records in patients with multidrug-resistant Gram-negative infection. International Journal of Antimicrobial Agents 64 , 107175 (2024). Lundberg, S. M. et al. From Local Explanations to Global Understanding with Explainable AI for Trees. Nat Mach Intell 2 , 56–67 (2020). Petch, J., Di, S. & Nelson, W. Opening the Black Box: The Promise and Limitations of Explainable Machine Learning in Cardiology. Can J Cardiol 38 , 204–213 (2022). DecisionLinnc Core Team. DecisionLinnc is a platform that integrates multiple programming language environments and enables data processing, data analysis, and machine learning through a visual interface. Statsape Co.Ltd (2023). Oxman, D. et al. Incidence of Multidrug Resistant Infections in Emergency Department Patients with Suspected Sepsis. The American Journal of the Medical Sciences 360 , 650–655 (2020). González-Anleo, C. et al. Risk factors for multidrug-resistant bacteria in critically ill children and MDR score development. European Journal of Pediatrics 183 , 5255–5265 (2024). Diseases N. C. F. C. & China T. W. C. O. T. R. O. C. H. A. D. I. Summary of China Cardiovascular Health and Disease Report 2024. Chinese Circulation Journal 40 , 521–559 (2025). Murray, E. C. et al. Therapeutic targeting of inflammation in hypertension: from novel mechanisms to translational perspective. Cardiovasc Res 117 , 2589–2609 (2021). Douna, H. et al. B- and T-lymphocyte attenuator stimulation protects against atherosclerosis by regulating follicular B cells. Cardiovasc Res 116 , 295–305 (2020). Guzik, T. J., Nosalski, R., Maffia, P. & Drummond, G. R. Immune and inflammatory mechanisms in hypertension. Nature Reviews Cardiology 21 , 396–416 (2024). Gomez, H. et al. A unified theory of sepsis-induced acute kidney injury: inflammation, microcirculatory dysfunction, bioenergetics, and the tubular cell adaptation to injury. Shock 41 , 3–11 (2014). Zarbock, A., Gomez, H. & Kellum, J. A. Sepsis-induced acute kidney injury revisited: pathophysiology, prevention and future therapies. Curr Opin Crit Care 20 , 588–595 (2014). Oweis, A. O., Zeyad, H. N., Alshelleh, S. A. & Alzoubi, K. H. Acute Kidney Injury Among Patients with Multi-Drug Resistant Infection: A Study from Jordan. Journal of Multidisciplinary Healthcare Volume 15 , 2759–2766 (2022). Thille, A. W. et al. Effect of Postextubation High-Flow Nasal Oxygen With Noninvasive Ventilation vs High-Flow Nasal Oxygen Alone on Reintubation Among Patients at High Risk of Extubation Failure: A Randomized Clinical Trial. JAMA 322 , 1465–1475 (2019). Rosenberg, K. Lower Reintubation Risk with Noninvasive Ventilation Plus High-Flow Nasal Oxygen. Am J Nurs 120 , 50 (2020). Li, N., Zhou, H. & Tang, Q. Red Blood Cell Distribution Width: A Novel Predictive Indicator for Cardiovascular and Cerebrovascular Diseases. Dis Markers 2017 , 7089493 (2017). Yčas, J. W. Toward a Blood-Borne Biomarker of Chronic Hypoxemia: Red Cell Distribution Width and Respiratory Disease. Adv Clin Chem 82 , 105–197 (2017). Lu, X. et al. Prognostic significance of increased preoperative red cell distribution width (RDW) and changes in RDW for colorectal cancer. Cancer Med 12 , 13361–13373 (2023). Wu, H. et al. Diagnostic value of RDW for the prediction of mortality in adult sepsis patients: A systematic review and meta-analysis. Front. Immunol. 13 , (2022). Kvacskay, P. et al. Increase of aerobic glycolysis mediated by activated T helper cells drives synovial fibroblasts towards an inflammatory phenotype: new targets for therapy? Arthritis Res Ther 23 , 56 (2021). Yue et al. Machine learning for the prediction of acute kidney injury in patients with sepsis. Journal of Translational Medicine 20 , (2022). Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted 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-8242432","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":565303816,"identity":"f20ab666-02f2-48ec-b9b9-e9b1d19b32d1","order_by":0,"name":"Qianqian Zhang","email":"","orcid":"","institution":"Anhui University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Qianqian","middleName":"","lastName":"Zhang","suffix":""},{"id":565303817,"identity":"c6039a73-008b-44f4-8bd6-2cd89694f646","order_by":1,"name":"Nianzhi Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABFElEQVRIiWNgGAWjYDACCTjJw3D45x8bOX5m5oMPiNfC2JBmLNnOlmxAhBYGsBZmxoZDiQbnecwE8OmQn9387OHXHRby5vxnDx4u3HEgwfgwgxkDQ41NNC4tjHOOmRvLnpEw3NlwLuHwzDN38swOM6Q9YDiWltuAQwuzRIKZtGSbBOOGgz0GB3jYnhUDtRw3YGw4jFMLm0T6N5AW+w2HeUBaDidubmYEmoBHC49EjpnkxzaJxA3HeAwO87YdTtzAzMyGV4uERE6ZNNDY5A1neAwOzjiTZixxmI3ZIAGPX+RnpG+T/NlWZ7vh/BnjDx8qgFHZf/7jgw81Nji1gIOAB0MoAY9yEGD8QUDBKBgFo2AUjHAAACFtXcKTxDwHAAAAAElFTkSuQmCC","orcid":"","institution":"First Affiliated Hospital of Anhui University of Traditional Chinese Medicine","correspondingAuthor":true,"prefix":"","firstName":"Nianzhi","middleName":"","lastName":"Zhang","suffix":""},{"id":565303822,"identity":"ee9809d4-4cdb-4612-92fa-77547a503e80","order_by":2,"name":"Ying Zheng","email":"","orcid":"","institution":"Anhui University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Ying","middleName":"","lastName":"Zheng","suffix":""},{"id":565303825,"identity":"4a877bff-b6b6-4226-bacc-3ce0fbc80d26","order_by":3,"name":"Jing Zhou","email":"","orcid":"","institution":"First Affiliated Hospital of Anhui University of Traditional Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Jing","middleName":"","lastName":"Zhou","suffix":""},{"id":565303829,"identity":"7a42734e-dd6b-4186-86e8-47eadcdeff65","order_by":4,"name":"Ling Liu","email":"","orcid":"","institution":"First Affiliated Hospital of Anhui University of Traditional Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Ling","middleName":"","lastName":"Liu","suffix":""}],"badges":[],"createdAt":"2025-11-30 13:53:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8242432/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8242432/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":99318931,"identity":"7cc69eaa-15ad-4e27-93f0-5575be69d76c","added_by":"auto","created_at":"2025-12-31 16:35:44","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":864377,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.docx","url":"https://assets-eu.researchsquare.com/files/rs-8242432/v1/0a3dbe7b2a226415771ce1ae.docx"},{"id":99193094,"identity":"d9fd3e97-08de-49f3-ba48-3286100d5d17","added_by":"auto","created_at":"2025-12-30 01:18:29","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6260,"visible":true,"origin":"","legend":"","description":"","filename":"a97261256086464298ebfc3a08dc0a9c.json","url":"https://assets-eu.researchsquare.com/files/rs-8242432/v1/253c5d8bab3807712067b942.json"},{"id":99193098,"identity":"c770d9b1-91ff-4898-b072-dca93bfae086","added_by":"auto","created_at":"2025-12-30 01:18:29","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":109909,"visible":true,"origin":"","legend":"","description":"","filename":"a97261256086464298ebfc3a08dc0a9c1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8242432/v1/7debc634f6b1279982244939.xml"},{"id":99193095,"identity":"87ed0c36-255a-46a0-a67d-3fac187db1fe","added_by":"auto","created_at":"2025-12-30 01:18:29","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":132023,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8242432/v1/f41b08efaaa0f938e3daebea.png"},{"id":99193116,"identity":"9e123635-a1cd-432b-a65e-d888d7f7b386","added_by":"auto","created_at":"2025-12-30 01:18:29","extension":"jpeg","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1594080,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8242432/v1/e406f9d5128067f3696fa905.jpeg"},{"id":99193101,"identity":"f6ff3dec-4396-431e-a754-3d1c7ed2c9b6","added_by":"auto","created_at":"2025-12-30 01:18:29","extension":"jpeg","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1224126,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8242432/v1/4b45c63a78360ae21a6d0e2c.jpeg"},{"id":99317289,"identity":"d0861142-67d4-4692-9f88-165cb4f8ff71","added_by":"auto","created_at":"2025-12-31 16:29:55","extension":"jpeg","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2630842,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8242432/v1/dc522424867c8a78a0f942f7.jpeg"},{"id":99193104,"identity":"c56c068b-2745-48fc-9bb8-bbee02cac77b","added_by":"auto","created_at":"2025-12-30 01:18:29","extension":"jpeg","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2835750,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8242432/v1/0a6ff81b14af6d57e9ddb39d.jpeg"},{"id":99193102,"identity":"44732310-ee22-4c15-a946-c933ac74a019","added_by":"auto","created_at":"2025-12-30 01:18:29","extension":"jpeg","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":47196,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8242432/v1/3f5517cd012de4bf2760a9c9.jpeg"},{"id":99193105,"identity":"bbc3b61b-407a-4a8f-9891-fa30e66c7599","added_by":"auto","created_at":"2025-12-30 01:18:29","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":27132,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8242432/v1/ae8d9a055a6fd96452aeed65.png"},{"id":99193112,"identity":"c60ab421-ec47-4a3d-a434-64e86bbb2674","added_by":"auto","created_at":"2025-12-30 01:18:29","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":23276,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8242432/v1/c92a19b29b0686d77012fc08.png"},{"id":99193113,"identity":"7bcbce31-5504-44bf-a034-cfbd965af514","added_by":"auto","created_at":"2025-12-30 01:18:29","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":28583,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8242432/v1/48ac0a70ce520e81b3f3fd8b.png"},{"id":99193111,"identity":"d92df2ad-9179-4367-a67c-8a178c3897b3","added_by":"auto","created_at":"2025-12-30 01:18:29","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20405,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8242432/v1/44cf4f8e3db202a1e103cc6a.png"},{"id":99317068,"identity":"9715436b-8306-47cc-814f-88e7233e3931","added_by":"auto","created_at":"2025-12-31 16:29:37","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":51617,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8242432/v1/c9a6d7870fdd4bf851b937a2.png"},{"id":99193106,"identity":"084b870c-7100-4456-ab01-6041aa13bd85","added_by":"auto","created_at":"2025-12-30 01:18:29","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":19349,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-8242432/v1/8df0c7ff356491192873fafa.png"},{"id":99193114,"identity":"08601adb-1626-4aea-a53c-da7616a614b3","added_by":"auto","created_at":"2025-12-30 01:18:29","extension":"xml","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":111877,"visible":true,"origin":"","legend":"","description":"","filename":"a97261256086464298ebfc3a08dc0a9c1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8242432/v1/e2b2991a200fb2297ef8cffb.xml"},{"id":99193108,"identity":"7c6f1c83-9adb-48c8-a66e-e60670264c62","added_by":"auto","created_at":"2025-12-30 01:18:29","extension":"html","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":123506,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8242432/v1/bd0727cebd630d6457b9e72b.html"},{"id":99193093,"identity":"4f3b1c3f-ed00-4802-94e0-67c8a6cc641e","added_by":"auto","created_at":"2025-12-30 01:18:29","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":97772,"visible":true,"origin":"","legend":"\u003cp\u003eParticipant Selection Flowchart.\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-8242432/v1/9d94bc0002f880dc1bc8b1be.png"},{"id":99317805,"identity":"6a98e6ce-8811-47cc-9a57-f952d5f90a77","added_by":"auto","created_at":"2025-12-31 16:30:43","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":81599,"visible":true,"origin":"","legend":"\u003cp\u003e(A) LASSO path of selected features (B) Boruta feature importance plot\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-8242432/v1/ae721e1ac73abf47f4cfa04c.png"},{"id":99317330,"identity":"9a854516-8c41-43aa-b1fb-1e1d09d3d6e4","added_by":"auto","created_at":"2025-12-31 16:30:01","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":82302,"visible":true,"origin":"","legend":"\u003cp\u003eMachine learning model for construction and diagnostic efficiency evaluation of Broussonetia papyrifera. (A) ROC curve; (B) DCA curve; (C) Calibration plot.\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-8242432/v1/a4572d9b6911fd23dfd2de48.png"},{"id":99193110,"identity":"bb5c2f4d-c991-417d-92f5-8faec0bd0a47","added_by":"auto","created_at":"2025-12-30 01:18:29","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":73336,"visible":true,"origin":"","legend":"\u003cp\u003e(A) SHAP variable importance ranking of the LGBMTEST model. (B) SHAP variable swarm plot.\u003c/p\u003e","description":"","filename":"4.png","url":"https://assets-eu.researchsquare.com/files/rs-8242432/v1/b59cd2369a4dec87af536890.png"},{"id":99317024,"identity":"1d7f70b1-27d6-4387-888b-3951ea582f76","added_by":"auto","created_at":"2025-12-31 16:29:36","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":188323,"visible":true,"origin":"","legend":"\u003cp\u003eThe SHAP dependency plots for the top six variables in the LGBMTEST model are displayed, including HTN, AKI, lactic acid, RDW, APSIII, and PO2.\u003c/p\u003e","description":"","filename":"5.png","url":"https://assets-eu.researchsquare.com/files/rs-8242432/v1/09efc41148da0d5b2c494f6e.png"},{"id":99316893,"identity":"aa88b1c7-e427-4431-b935-c3e85b0018ee","added_by":"auto","created_at":"2025-12-31 16:29:23","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":80550,"visible":true,"origin":"","legend":"\u003cp\u003e(A) SHAP waterfall plot \u0026nbsp;(B) SHAP force plot\u003c/p\u003e","description":"","filename":"6.png","url":"https://assets-eu.researchsquare.com/files/rs-8242432/v1/d081f7e61a0ff9b6b91e4473.png"},{"id":100405633,"identity":"500d6486-63b6-4e8a-b07f-7f7578dbc9f9","added_by":"auto","created_at":"2026-01-16 12:09:09","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1876001,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8242432/v1/8ea58810-b647-45d4-8f48-a3bdb17e9ff4.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Machine learning prediction and interpretive analysis of multidrug-resistant microbial infection risk in septicemia patients: A study from the MIMIC-IV database​","fulltext":[{"header":"Introduction","content":"\u003cp\u003eSepsis is a life-threatening organ dysfunction caused by a dysregulated host response to infection. As a common critical condition in emergency departments and ICUs, its mortality rate exceeds that of myocardial infarction and stroke\u0026nbsp;[1]. Among the approximately 49 million sepsis cases worldwide annually, 11 million patients die from sepsis-related complications, accounting for 20% of global Homo sapiens deaths\u0026nbsp;[2]. The latest epidemiological study in China reveals that the incidence of sepsis in ICU patients reaches 20.6%, with a mortality rate as high as 35.5%. Among Gram-negative bacterial infection cases, 42% involve multidrug-resistant organisms (MDROs), which are significantly associated with mortality\u0026nbsp;[3]. More alarmingly, the risk of death in MDRO-infected patients is 64% higher than in those with non-resistant infections\u0026nbsp;[4], making Broussonetia papyrifera a core challenge in critical care.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;MDROs refer to pathogens resistant to three or more classes of commonly used antimicrobial agents, encompassing extensively drug-resistant (XDR) and pan-drug-resistant (PDR) strains. Clinically common MDROs include methicillin-resistant Staphylococcus aureus (MRSA), vancomycin-resistant enterococci (VRE), extended-spectrum β-lactamase (ESBL)-producing Enterobacteriaceae, and multidrug-resistant Pseudomonas aeruginosa (MDR-PA)\u0026nbsp;[5]. Data from the 2020 China Bacterial Resistance Surveillance Report show that the top five pathogens with the highest clinical dissociation rates are Escherichia coli (18.96%), Klebsiella pneumoniae (14.12%), Staphylococcus aureus (8.93%), Pseudomonas aeruginosa (7.96%), and Acinetobacter baumannii (7.28%)\u0026nbsp;[4]. Notably, detection rates of MRSA (28.5%→30.2%) and carbapenem-resistant Klebsiella pneumoniae (10.4%→13.3%) continued to rise between 2018 and 2021\u0026nbsp;[6], reflecting an increasingly severe resistance crisis\u0026nbsp;[7,8].\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eGiven the complexity and rapid progression of sepsis, early and accurate prediction of MDRO infection risk poses significant challenges\u0026nbsp;[9]. Traditional scoring systems (e.g., SOFA, APACHE II) are limited in capturing complex nonlinear relationships among variables. Therefore, there is an urgent need to develop dynamic risk prediction tools by integrating machine learning (ML) techniques. The widespread adoption of electronic health records (EHRs) in Broussonetia papyrifera healthcare institutions provides rich clinical data resources for such risk predictions. ML excels at processing complex high-dimensional data and identifying nonlinear patterns, demonstrating great potential in disease prediction\u0026nbsp;[10]. Due to its efficiency, accuracy, and ability to handle high-dimensional data, ML applications in healthcare are becoming increasingly prevalent\u0026nbsp;[11–13]. Preliminary studies have confirmed the feasibility of ML in predicting MDRO infections[14][15]\u0026nbsp;; however, the \"black-box\" nature of ML models (lack of interpretability) limitstheir clinical adoption\u0026nbsp;[16]. The SHapley Additive exPlanations (SHAP) method quantifies feature contributions to provide intuitive explanations for model predictions\u0026nbsp;[17], thereby addressing the black-box problem. Thus, this study aims to: 1. Utilize the large-scale critical care database MIMIC-IV; 2. Systematically identify key risk factors for MDRO infections in ICU sepsis patients; 3. Broussonetia papyrifera develops and compares multiple ML prediction models;\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e4. Apply SHAP to elucidate model prediction mechanisms, enhance transparency and clinical acceptance, and optimize prevention, control, and management decisions for MDRO infections in ICU sepsis patients.\u003c/p\u003e"},{"header":"Methods","content":"\u003cp\u003e\u003cstrong\u003e2.1. Data Sources and Study Cohort\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis retrospective analysis was conducted using the Medical Information Mart for Intensive Care IV database (MIMIC-IV v3.1), jointly developed by the Massachusetts Institute of Technology (MIT) Computational Physiology and Artificial Intelligence Laboratory and Beth Israel Deaconess Medical Center (BIDMC). The database incorporates significant improvements, including data updates and structural optimizations. The dataset encompasses over 360,000 patient care trajectories from the BIDMC intensive care unit in Boston, USA, between 2008 and 2022, involving more than 540,000 hospitalization records and over 90,000 ICU stays. It includes multidimensional clinical features, such as demographic information, laboratory test results, medication records, continuous vital sign monitoring data, surgical procedure codes, ICD-standardized diagnostic information, therapeutic regimens, and post-discharge survival follow-up. \u0026nbsp;The BIDMC Institutional Review Board approved the study as meeting the criteria for data use exemption. The research team obtained access (ID: 14280276) after completing the National Institutes of Health (NIH) Human Subjects Protection Course and the Collaborative Institutional Training Initiative (CITI) program. The database employs dual de-identification techniques, with all protected health information (PHI) removed, complying with the Health Insurance Portability and Accountability Act (HIPAA) Safe Harbor standards, thus waiving the need for informed consent.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e2.2. Inclusion and Exclusion Criteria\u003c/p\u003e\n\u003cp\u003eInclusion criteria:\u003c/p\u003e\n\u003cp\u003ePatients meeting both of the following criteria based on the Sepsis-3.0 definition were included:\u003c/p\u003e\n\u003cp\u003eSuspected or confirmed infection\u003c/p\u003e\n\u003cp\u003eSOFA score\u0026nbsp;\u0026ge;\u0026nbsp;2 points within 24 hours of ICU admission\u003c/p\u003e\n\u003cp\u003eExclusion criteria:\u003c/p\u003e\n\u003cp\u003eSubjects were excluded if any of the following applied:\u003c/p\u003e\n\u003cp\u003eMultiple ICU admissions during same hospitalization (only first admission retained)\u003c/p\u003e\n\u003cp\u003ei. ICU length of stay \u0026lt; 24 hours\u003c/p\u003e\n\u003cp\u003eii. Age \u0026lt; 18 or \u0026gt; 90 years\u003c/p\u003e\n\u003cp\u003eiii. SOFA score not documented within 24 hours of ICU admission\u003c/p\u003e\n\u003cp\u003eiv. No microbiological culture performed within 48 hours of admission\u003c/p\u003e\n\u003cp\u003eV. \u0026nbsp;A detailed patient selection flowchart is presented in Figure 1.\u003c/p\u003e\n\u003cp\u003eFig. 1\u003c/p\u003e\n\u003cp\u003eParticipant Selection Flowchart.\u003c/p\u003e\n\u003cp\u003e2.3 Data Extraction\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eData extraction was performed using Navicat Premium (Version 16.1.15) and Structured Query Language (SQL). This study explored several dimensions of sepsis patients in the MIMIC-IV database: (1) Demographic characteristics: age, sex, weight, marital status, ethnicity, language. (2) Comorbidities: HTN, AKI, AKD, T2DM. (3) Initial vital signs upon ICU admission: heart rate (HR), blood pressure parameters (systolic pressure SBP/diastolic pressure DBP/mean arterial pressure MBP), respiratory rate (RR), body temperature (T), and blood oxygen saturation (SpO2). (4) Laboratory indicators: including blood gas analysis (tCO2, iCa, Lac, PaCO2, pH, PaO2), RDW, serum albumin (ALB), complete blood cell count (red blood cells, white blood cells, platelets), blood glucose and electrolytes (Na+, K+, anion gap), and microbiological culture results (positive/negative, specific pathogens, and drug resistance). (5) Disease severity scores: Sequential Organ Failure Assessment (SOFA), APS III. (6) Interventions received by VAP patients: duration of mechanical ventilation. (7) Outcome measures: in-hospital mortality, ICU mortality, 28-day mortality, with the primary endpoint focusing on the incidence of MDRO infection in sepsis patients during ICU hospitalization.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e2.4 Data Processing\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eVariables with missing values exceeding 25% were removed. Continuous variables were processed using Winsorization (1% and 99% percentiles) to handle outliers, while missing categorical variables were imputed using the mode. Categorical variables with category percentages less than 5% or containing ambiguous classifications were excluded. The retained variables were subsequently used for further analysis. To avoid data contamination, the dataset was first randomly divided into training and validation sets in a 7:3 ratio. The training set was used for feature selection and model training, while the test set was solely for final performance evaluation. Subsequently, the interpolate function in Python was used to impute data for the training and validation sets separately using the spline method.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e2.5 Statistical Analysis and Model Development\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eBaseline characteristics were described using statistical tests appropriate to data distribution. Continuous variables underwent normality testing with the Kolmogorov-Smirnov test, with intergroup comparisons performed using t-tests for normally distributed data. Categorical variables were presented as percentages (%) and compared using Pearson\u0026apos;s chi-square test.\u003c/p\u003e\n\u003cp\u003eTo address class imbalance (12.1% MDRO-positive rate), we implemented the Synthetic Minority Oversampling Technique (SMOTE). Oversampling was applied exclusively during five-fold cross-validation partitioning, which divided the sample data into training and internal validation sets.\u003c/p\u003e\n\u003cp\u003eSix machine learning algorithms were employed for model construction: Light Gradient Boosting Machine (LGBM), Random Forest (RF), Categorical Boosting (CatBoost), Gradient Boosting Decision Tree (GBDT), K-Nearest Neighbor Classification (KNNC), and Multilayer Perceptron (MLP). Variables selected by LASSO regression comprised the candidate feature set for subsequent Boruta algorithm screening and model input. Hyperparameter tuning optimized models by maximizing the area under the receiver operating characteristic (ROC) curve (AUC).\u003c/p\u003e\n\u003cp\u003eModel performance was comprehensively evaluated using AUC, sensitivity, specificity, accuracy, F1-score, and recall. Clinical utility was further assessed through decision curve analysis (DCA) and calibration curve plotting.\u003c/p\u003e\n\u003cp\u003eModel interpretation incorporated three SHapley Additive exPlanations (SHAP) visualization techniques: summary plots for global feature importance, dependence plots to illustrate nonlinear relationships between key continuous variables and predicted risk, and swarm plots (beeswarm plots) for individual sample-level interpretation.\u003c/p\u003e\n\u003cp\u003eAll analyses were performed using DecisionLinnc 1.0 software (Decision Medicine Inc.), which provides a visual statistical workflow interface\u0026nbsp;[18]. Statistical significance was defined as p \u0026lt; 0.05.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e3.1 Baseline Characteristics\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eA total of 23,191 participants were enrolled from the MIMIC-IV dataset: 20,385 (87.9%) in the non-MDRO group and 2,806 (12.1%) in the MDRO group. Table 1 provides a detailed comparative analysis of baseline characteristics.\u003c/p\u003e\n\u003cp\u003ePatients with MDRO infection were slightly younger (64.57 \u0026plusmn; 15.16 years vs. 65.45 \u0026plusmn; 15.42 years,\u0026nbsp;P\u0026lt; 0.001), while weight showed no significant difference (85.44 \u0026plusmn; 26.76 kg vs. 83.81 \u0026plusmn; 23.56 kg,\u0026nbsp;P= 0.111). Laboratory analysis revealed that the MDRO group had significantly lower hemoglobin (10.20 \u0026plusmn; 2.27 g/dL vs. 10.51 \u0026plusmn; 2.27 g/dL,\u0026nbsp;P\u0026lt; 0.001) and sodium levels (137.98 \u0026plusmn; 6.12 mmol/L vs. 138.35 \u0026plusmn; 5.41 mmol/L,\u0026nbsp;P\u0026lt; 0.001). Conversely, this group exhibited higher platelet counts (209.29 \u0026plusmn; 126.39 \u0026times;10\u0026sup3;/\u0026mu;L vs. 196.06 \u0026plusmn; 108.63 \u0026times;10\u0026sup3;/\u0026mu;L,\u0026nbsp;P\u0026lt; 0.001), RDW (15.86 \u0026plusmn; 2.63% vs. 15.05 \u0026plusmn; 2.38%,\u0026nbsp;P\u0026lt; 0.001), glucose (153.72 \u0026plusmn; 82.36 mg/dL vs. 149.93 \u0026plusmn; 81.47 mg/dL,\u0026nbsp;P= 0.002), lactate (2.50 \u0026plusmn; 2.10 mmol/L vs. 2.44 \u0026plusmn; 1.93 mmol/L,\u0026nbsp;P= 0.044), anion gap (15.01 \u0026plusmn; 4.69 mmol/L vs. 14.52 \u0026plusmn; 4.75 mmol/L,\u0026nbsp;P\u0026lt; 0.001), creatinine (1.71 \u0026plusmn; 1.61 mg/dL vs. 1.50 \u0026plusmn; 1.60 mg/dL,\u0026nbsp;P\u0026lt; 0.001), and BUN (32.72 \u0026plusmn; 26.37 mg/dL vs. 27.69 \u0026plusmn; 23.15 mg/dL,\u0026nbsp;P\u0026lt; 0.001). Partial pressure of oxygen (PaO₂) was significantly lower in the MDRO group (130.07 \u0026plusmn; 99.00 mm Hg vs. 167.26 \u0026plusmn; 123.93 mm Hg,\u0026nbsp;P\u0026lt; 0.001).Disease severity scores were significantly higher in the MDRO infection group: SOFA (6.76 \u0026plusmn; 3.93 vs. 5.99 \u0026plusmn; 3.46,\u0026nbsp;P\u0026lt; 0.001) and APS III (57.25 \u0026plusmn; 23.13 vs. 49.58 \u0026plusmn; 21.99,\u0026nbsp;P\u0026lt; 0.001). Comorbidity analysis showed significantly higher prevalence of AKI (55.38% vs. 39.93%,\u0026nbsp;P\u0026lt; 0.001), CKD (21.28% vs. 18.01%,\u0026nbsp;P\u0026lt; 0.001), and T2DM (33.54% vs. 28.60%,\u0026nbsp;P\u0026lt; 0.001) among MDRO patients, while hypertension prevalence was lower (37.28% vs. 42.05%,\u0026nbsp;P\u0026lt; 0.001). The MDRO group also exhibited higher utilization of mechanical ventilation (63.26% vs. 51.90%,\u0026nbsp;P\u0026lt; 0.001).Clinical outcomes demonstrated significantly higher 28-day mortality in the MDRO infection group (22.77% vs. 18.14%,\u0026nbsp;P\u0026lt; 0.001).\u003c/p\u003e\n\u003cp\u003eTable 1 \u0026nbsp;\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003eVariable\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003eOverall\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003eNon-MDRO-Sepsis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003eMDRO-Sepsis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003ep-value\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003eN = 23,191\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003eN = 20,385\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003eN = 2,806\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003eAge(years)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e65.34 \u0026plusmn; 15.39\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e65.45 \u0026plusmn; 15.42\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e64.57 \u0026plusmn; 15.16\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\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: 20%;\"\u003e\n \u003cp\u003eWeight(kg)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e84.01 \u0026plusmn; 23.97\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e83.81 \u0026plusmn; 23.56\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e85.44 \u0026plusmn; 26.76\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e0.111\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003eHemoglobin(g/dL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e10.48 \u0026plusmn; 2.27\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e10.51 \u0026plusmn; 2.27\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e10.20 \u0026plusmn; 2.27\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\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: 20%;\"\u003e\n \u003cp\u003ePlatelet(K/uL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e197.66 \u0026plusmn; 111.01\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e196.06 \u0026plusmn; 108.63\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e209.29 \u0026plusmn; 126.39\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\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: 20%;\"\u003e\n \u003cp\u003eRDW(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e15.15 \u0026plusmn; 2.43\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e15.05 \u0026plusmn; 2.38\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e15.86 \u0026plusmn; 2.63\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\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: 20%;\"\u003e\n \u003cp\u003eRBC(m/uL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e3.50 \u0026plusmn; 0.79\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e3.51 \u0026plusmn; 0.78\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e3.43 \u0026plusmn; 0.80\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\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: 20%;\"\u003e\n \u003cp\u003eWBC(K/uL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e13.47 \u0026plusmn; 10.64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e13.35 \u0026plusmn; 9.86\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e14.33 \u0026plusmn; 15.11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e0.102\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003eAnion gap(m/EqL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e14.58 \u0026plusmn; 4.75\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e14.52 \u0026plusmn; 4.75\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e15.01 \u0026plusmn; 4.69\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\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: 20%;\"\u003e\n \u003cp\u003eGlucose(mg/dL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e150.38 \u0026plusmn; 81.59\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e149.93 \u0026plusmn; 81.47\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e153.72 \u0026plusmn; 82.36\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e0.002\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003ePotassium(m/EqL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e4.24 \u0026plusmn; 0.77\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e4.24 \u0026plusmn; 0.76\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e4.25 \u0026plusmn; 0.82\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e0.733\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003eSodium(m/EqL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e138.30 \u0026plusmn; 5.50\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e138.35 \u0026plusmn; 5.41\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e137.98 \u0026plusmn; 6.12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\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: 20%;\"\u003e\n \u003cp\u003eLactate(mmol/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e2.45 \u0026plusmn; 1.95\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e2.44 \u0026plusmn; 1.93\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e2.50 \u0026plusmn; 2.10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e0.044\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003ePco2(mmHg)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e42.46 \u0026plusmn; 11.36\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e42.39 \u0026plusmn; 11.14\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e42.98 \u0026plusmn; 12.86\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e0.735\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003ePO2(mmHg)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e162.76 \u0026plusmn; 121.79\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e167.26 \u0026plusmn; 123.93\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e130.07 \u0026plusmn; 99.00\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\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: 20%;\"\u003e\n \u003cp\u003eCreatinine(mg/dL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e1.53 \u0026plusmn; 1.60\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e1.50 \u0026plusmn; 1.60\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e1.71 \u0026plusmn; 1.61\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\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: 20%;\"\u003e\n \u003cp\u003eUrea nitrogen(mg/dL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e28.30 \u0026plusmn; 23.62\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e27.69 \u0026plusmn; 23.15\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e32.72 \u0026plusmn; 26.37\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\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: 20%;\"\u003e\n \u003cp\u003eSOFA(score)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e6.08 \u0026plusmn; 3.53\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e5.99 \u0026plusmn; 3.46\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e6.76 \u0026plusmn; 3.93\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\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: 20%;\"\u003e\n \u003cp\u003eAPSIII(score)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e50.51 \u0026plusmn; 22.27\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e49.58 \u0026plusmn; 21.99\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e57.25 \u0026plusmn; 23.13\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\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: 20%;\"\u003e\n \u003cp\u003eIcu survival time(days)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e46.64 \u0026plusmn; 205.73\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e47.52 \u0026plusmn; 211.59\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e40.31 \u0026plusmn; 156.57\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e0.077\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003eGender\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\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: 20%;\"\u003e\n \u003cp\u003eFemale\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e9,391.00 (40.49%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e8,134.00 (39.90%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e1,257.00 (44.80%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003eMale\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e13,800.00 (59.51%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e12,251.00 (60.10%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e1,549.00 (55.20%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003eVentilation\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\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: 20%;\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e10,837.00 (46.73%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e9,806.00 (48.10%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e1,031.00 (36.74%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003eYes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e12,354.00 (53.27%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e10,579.00 (51.90%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e1,775.00 (63.26%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003eHTN\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\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: 20%;\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e13,573.00 (58.53%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e11,813.00 (57.95%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e1,760.00 (62.72%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003eYes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e9,618.00 (41.47%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e8,572.00 (42.05%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e1,046.00 (37.28%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003eAKI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\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: 20%;\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e13,497.00 (58.20%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e12,245.00 (60.07%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e1,252.00 (44.62%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003eYes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e9,694.00 (41.80%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e8,140.00 (39.93%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e1,554.00 (55.38%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003eCKD\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\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: 20%;\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e18,923.00 (81.60%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e16,714.00 (81.99%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e2,209.00 (78.72%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003eYes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e4,268.00 (18.40%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e3,671.00 (18.01%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e597.00 (21.28%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003eT2DM\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\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: 20%;\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e16,419.00 (70.80%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e14,554.00 (71.40%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e1,865.00 (66.46%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003eYes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e6,772.00 (29.20%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e5,831.00 (28.60%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e941.00 (33.54%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003eDeath within icu 28days\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\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: 20%;\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e18,855.00 (81.30%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e16,688.00 (81.86%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e2,167.00 (77.23%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003eYes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e4,336.00 (18.70%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e3,697.00 (18.14%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e639.00 (22.77%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 20%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003eCharacteristics of MDRO-Sepsis and non-MDRO-Sepsis patients in the MIMIC-IV database. Continuous variables are expressed as mean \u0026plusmn; SD, and categorical variables are expressed as n(%).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e3.2 Feature Selection\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eFrom the initial pool of 40 clinical features, we performed a two-stage feature selection using LASSO regression followed by the Boruta algorithm. Figure 2A presents the LASSO coefficient shrinkage path, demonstrating how feature coefficients converged to zero with increasing regularization strength (\u0026lambda;). This process identified 24 features for further consideration. Subsequent Boruta analysis, illustrated in Figure 2B, confirmed 20 features with importance scores significantly exceeding those of permuted shadow features. The intersection of features identified by both methods yielded nine final predictors: age, platelet count, RDW, glucose, lactate, PaO₂, APS III, HTN, and AKI.\u003c/p\u003e\n\u003cp\u003eFig.2\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e3.3 Model Performance Comparison\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eIn our study, six ML models were developed to assess the risk of multiple drug resistance (MDR) bacterial infection in ICU sepsis patients (Table 2). The LGBM model demonstrated the best performance: AUC=0.964, accuracy=0.904, F1-score=0.925, MCC=0.79.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eThe CatBoost and KNNC models also performed well (AUC=0.930 and 0.914, respectively). The GBDT, MLP, and RF models showed relatively weaker performance (AUC=0.843, 0.867, and 0.831, respectively). The ROC curve (Figure 3A) visually illustrates the discriminative power of each model, with the LGBM curve being closest to the top-left corner. Decision curve analysis (DCA, Figure 3B) revealed that across a wide range of risk thresholds (particularly 0.2\u0026ndash;0.6), the clinical net benefits provided by the LGBM and CatBoost models were significantly higher than those of other models and the \u0026quot;all-intervention\u0026quot; or \u0026quot;no-intervention\u0026quot; strategies. The calibration curve (Figure 3C) indicated good agreement between the predicted probabilities and actual risks for all models, with Brier scores \u0026lt;0.1 for all models, demonstrating excellent calibration.\u003c/p\u003e\n\u003cp\u003eTable 2\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 14.0598%;\"\u003e\n \u003cp\u003eModel Name\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003eAccuracy\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003ePrevalence\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003eRecall\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003eF1-Score\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.7627%;\"\u003e\n \u003cp\u003eMCC\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003eAUROC\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 14.0598%;\"\u003e\n \u003cp\u003eLGBMTEST\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.90\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.65\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.91\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.93\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.7627%;\"\u003e\n \u003cp\u003e0.79\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.96\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 14.0598%;\"\u003e\n \u003cp\u003eRFTEST\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.75\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.65\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.86\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.82\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.7627%;\"\u003e\n \u003cp\u003e0.43\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.83\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 14.0598%;\"\u003e\n \u003cp\u003eCatBoostTEST\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.85\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.65\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.88\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.88\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.7627%;\"\u003e\n \u003cp\u003e0.67\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.93\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 14.0598%;\"\u003e\n \u003cp\u003eGBDTTEST\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.84\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.65\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.89\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.88\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.7627%;\"\u003e\n \u003cp\u003e0.64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.84\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 14.0598%;\"\u003e\n \u003cp\u003eMLPTEST\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.83\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.65\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.94\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.88\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.7627%;\"\u003e\n \u003cp\u003e0.61\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.87\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 14.0598%;\"\u003e\n \u003cp\u003eKNNCTEST\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.86\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.65\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.98\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.90\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.7627%;\"\u003e\n \u003cp\u003e0.69\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.91\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 14.0598%;\"\u003e\n \u003cp\u003emean_scores\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.84\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.65\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.91\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.88\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.7627%;\"\u003e\n \u003cp\u003e0.64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 14.2355%;\"\u003e\n \u003cp\u003e0.89\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003eA comparative evaluation of performance metrics among the six models for internal validation.\u003c/p\u003e\n\u003cp\u003eFig. 3\u003c/p\u003e\n\u003cp\u003eMachine learning model for construction and diagnostic efficiency evaluation of Broussonetia papyrifera. (A) ROC curve; (B) DCA curve; (C) Calibration plot.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e3.4. Model Interpretation (SHAP Analysis)\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eGlobal feature importance display (Figure 4A): HTN and AKI are the top two risk drivers (mean SHAP \u0026gt;1.2), followed by RDW and APSIII. The influence of Platelet, Glucose, and Age is relatively minor. The SHAP beeswarm plot (Figure 4B) illustrates the direction (positive/negative) and magnitude of each feature\u0026apos;s contribution to the model output: HTN=1 (presence of hypertension) and AKI=1 (presence of acute kidney injury): Significantly increase MDRO infection risk (SHAP values concentrated in the positive range with higher magnitudes). High PO2 values significantly reduce risk (SHAP values concentrated in the negative range with lower magnitudes). High RDW values, high lactic acid values, and high APSIII values: Tend to increase risk.\u003c/p\u003e\n\u003cp\u003eFig. 4\u003c/p\u003e\n\u003cp\u003e(A) SHAP variable importance ranking of the LGBMTEST model. (B) SHAP variable swarm plot.\u003c/p\u003e\n\u003cp\u003eFigure 5 displays the top six variable SHAP dependence plots in the LGBMTEST model, including HTN, AKI, lactic acid, RDW, APSIII, and P02. When HTN and AKI are positive (value=1), the SHAP values are predominantly distributed in the positive range (0-4), indicating that patients with these complications have an infection risk increased by more than 1.8 times (Figures 5A, 5B). When lactate exceeds 4 mmol/L (Figure 5C), the SHAP value surpasses +2.0, marking the critical risk threshold for tissue hypoxia; RDW \u0026gt;15% (Figure 5D) sees the SHAP value leap above +3.0, making it the strongest independent risk factor and suggesting this metric may serve as a biomarker for immune dysregulation. Oxygenated status exhibits a nonlinear protective effect: when PO2 exceeds 300 mmHg, SHAP \u0026asymp; -2.5 (Figure 6F).\u003c/p\u003e\n\u003cp\u003eFig. 5\u003c/p\u003e\n\u003cp\u003eThe SHAP dependency plots for the top six variables in the LGBMTEST model are displayed, including HTN, AKI, lactic acid, RDW, APSIII, and PO2.\u003c/p\u003e\n\u003cp\u003eThe waterfall plot (Figure 6A) demonstrates a significant reduction in the predicted risk for this patient (total SHAP contribution value =-5.17), with key drivers being the absence of hypertension (HTN=0, SHAP=-0.956) and no concurrent acute kidney injury (AKI=0, SHAP=-0.734). The heatmap (Figure 6B) further confirms that all features exhibit negative contributions.\u003c/p\u003e\n\u003cp\u003eFig. 6\u003c/p\u003e"},{"header":"Discussion","content":"\u003cp\u003eThis study developed an interpretable predictive model for assessing the risk of MDRO infection in sepsis patients, employing SHAP values to unravel the model's complexity and identify key predictive factors. The results highlight the significance of HTN, AKI, lactic acid, RDW, APSIII, and P02 in ICU sepsis patients, underscoring their close association with MDRO infection.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e4.1 Discussion on Pathological Mechanisms\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eSepsis patients with MDRO infection face a significant clinical challenge, as these infections are often resistant to multiple antibiotics and are associated with prolonged ICU stays and increased mortality, directly impacting treatment outcomes and patient prognosis\u0026nbsp;[19]. Early identification of high-risk patients enables more targeted interventions, potentially improving recovery rates and alleviating the burden on healthcare resources. Given the rising prevalence of antibiotic-resistant infections in critical care settings, particularly those involving Broussonetia papyrifera\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e, predictive models are crucial for optimizing clinical decision-making and enhancing patient management\u0026nbsp;[20].\u003c/p\u003e\n\u003cp\u003eThrough SHAP dependency analysis, the combination of HTN and AKI was identified as a key factor in MDROs-sepsis risk. HTN[21]\u0026nbsp;is one of the core risk factors triggering stroke, ischemic heart disease, hypertensive heart disease, aortic aneurysm, and various other conditions. Although traditional cardiovascular risk factors (such as neuroendocrine, renal, and vascular systems) still play a dominant role in the development and progression of HTN, increasing evidence suggests that the immune system plays a non-negligible role in its pathogenesis and maintenance[22]. Immune cells (e.g., macrophages, CD4+ T cells, and CD8+ T cells), interleukins (ILs) (e.g., IL-6, IL-17A, IL-1β), and interferons (e.g., interferon-γ) within the immune system have been found to mediate hypertension and target organ damage[23]. Relevant studies indicate that hypertension may lead to immune homeostasis imbalance, vascular endothelial barrier disruption, and microbiota-drug metabolic disorder, which are associated with an increased risk of MDROs-sepsis[24], highlighting the potential link between altered immune status and susceptibility to MDROs infection.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eIn the complex mechanisms of sepsis-associated AKI, experimental models and clinical studies have demonstrated that inflammation-related molecules play a significant role in AKI development. Gomez et al.[25]proposed that sepsis-induced mechanisms collectively contribute to acute kidney injury, including inflammation and oxidative stress, microcirculatory dysfunction, tubular cell adaptation, and glomerular-glomerular feedback dysfunction. Other research[26]\u0026nbsp;suggests that the pathophysiology of sepsis-associated acute kidney injury involves alternating pro-inflammatory and anti-inflammatory changes, leading to microcirculatory alterations, endothelial dysfunction, thrombosis, cytokine release, and inflammatory response. AKI is often associated with altered immune status, treatment complexity, and potential polypharmacy, which may increase the risk of MDRO colonization and infection[27].\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eHowever, no studies have yet explored the relationship between comorbid hypertension and AKI with the etiology of MDROs-sepsis. We hypothesize that comorbid hypertension and AKI may reflect an immune homeostasis imbalance, rendering patients more susceptible to MDRO infection. Although this hypothesis is compelling to Homo sapiens, further investigation in future studies is necessary to establish a definitive link.\u003c/p\u003e\n\u003cp\u003eLow PO2 is a marker of sepsis severity and organ dysfunction and is associated with poor prognosis. Increasing blood oxygen concentration and arterial oxygen partial pressure can reduce postoperative wound infection rates and mortality in patients\u0026nbsp;[28]. This study further clarifies that low PO2 is an independent risk factor for MDRO infection, while high PO2 is a protective factor. This may reflect the association between oxygenated status and host defense capability or infection severity\u0026nbsp;[29]. RDW reflects red blood cell volume variability and is significantly elevated in chronic inflammation, oxidative stress, and tissue hypoxia, having been independently proven to predict mortality in cardiovascular diseases\u0026nbsp;[30], respiratory diseases\u0026nbsp;[31], and cancer patients\u0026nbsp;[32]. Previous studies indicate\u0026nbsp;[33]that RDW is a useful predictor of mortality in Homo sapiens sepsis patients. However, whether RDW can predict the risk of multiple drug resistance (MDR) bacterial infection in sepsis patients remains unclear. This study is the first to confirm that high RDW is a strong independent predictor of MDRO infection, suggesting its significant role warrants further investigation. Lactic acid participates in the regulation of numerous biological and pathological processes. It is known that hypoxia, inflammation, viral infection, and tumor microenvironments stimulate lactic acid production\u0026nbsp;[34]. Serum lactic acid levels serve as an important biomarker for sepsis, positively correlating with the incidence and mortality of sepsis or septic shock. High lactic acid levels indicate tissue hypoperfusion and shock. APS III is a comprehensive scoring system for assessing disease severity. Their elevated values align with increased MDRO infection risk, highlighting the importance of underlying disease severity in prediction.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e4.2 Comparison with Existing Studies and Innovations\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003ch3\u003eIn the field of early prediction of MDRO infection in sepsis patients, this study established six machine learning models (LGBM, RF, CatBoost, GBDT, MLP, KNNC) based on the MIMIC-IV database and Broussonetia papyrifera, and achieved model transparency through the SHAP method. Compared with traditional scoring systems (such as SOFA or APACHE II), SHAP deciphered the \"black box\" nature of machine learning models, providing both global and local interpretations, enabling clinicians to understand the prediction logic intuitively. DCA confirmed that the LGBM and CatBoost models demonstrated significant clinical net benefits within the risk threshold range of 20%–60% (Figure 3B), supporting their practical value in ICU settings.\u0026nbsp;\u003c/h3\u003e\n\u003ch3\u003eThe integration of the SHAP method enhanced interpretability, clarified the model's decision-making process, and provided a transparent and credible basis for assessing MDRO infection risk in sepsis patients. Similarly, another study\u0026nbsp;[35]\u0026nbsp;utilized SHAP values to evaluate the importance of features in their machine learning model for sepsis prediction, demonstrating that SHAP not only improved model interpretability but also strengthened clinicians' trust in the model's predictions. These findings underscore the value of SHAP in promoting the practical application of machine learning models in clinical settings, particularly for complex infections such as MDRO in sepsis patients.\u003c/h3\u003e\n\u003cp\u003e\u003cstrong\u003e4.3 Advantages and Limitations\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study utilized detailed clinical data from the MIMIC-IV database, employing database management and statistical software to streamline data extraction and processing, thereby reducing the workload associated with clinical data collection. Using six machine learning algorithms, a predictive model was developed with Broussonetia papyrifera to assess the risk of MDRO infection in ICU sepsis patients, an area with limited prior research. By incorporating the SHAP method, our study provided comprehensive global and local interpretations for the machine learning model, delving into its internal mechanisms. This work enhances interpretability, promotes a better understanding of the model's decision-making process, and establishes a transparent and credible foundation for evaluating the risk of MDRO infection in sepsis patients.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eHowever, certain limitations should be acknowledged. First, this was a single-center retrospective study, which may introduce hospital-specific biases. Healthcare practices, including ventilator settings, laboratory testing frequency, and infection control measures, may vary across hospitals due to Parazacco spilurus subsp. spilurus, potentially affecting the results. Future studies should consider multicenter research to account for these inter-hospital differences and yield more generalizable findings. Second, the outcome definition relied on microbial cultures, which may have missed culture-negative but clinically highly suspected MDRO infection cases (e.g., those already receiving broad-spectrum antibiotic therapy). The exclusion of antibiotic exposure history and invasive procedure data may also impact the model's generalizability. ICU stays shorter than 24 hours were excluded, potentially omitting sepsis patients who died or were discharged very early. Subsequent multicenter validation and the inclusion of additional factors (particularly antibiotic exposure) are essential and critical. Third, due to a large number of missing values, certain variables in the MIMIC-IV database were excluded, and the feature selection process may have omitted variables with significant impacts, potentially affecting the model's predictive performance. Finally, the use of SMOTE to address class imbalance may introduce biases related to synthetic data generation. Although SMOTE helps balance datasets, the generated synthetic samples may not fully reflect the complexity of real clinical scenarios for Phoxinus phoxinus subsp. phoxinus. Subsequent research will include multicenter external validation and incorporate other factors deemed crucial for further verifying model stability and performance.\u003c/p\u003e"},{"header":"Summary","content":"\u003cp\u003eSix machine learning models (LGBM, RF, CatBoost, GBDT, MLP, KNNC) were constructed for Broussonetia papyrifera, and their predictive performances were compared, revealing LGBM as the optimal model in terms of accuracy, discriminative ability, and identification of high-risk patients. The application of the SHAP method elucidated the key contributors to this model, including HTN, AKI, PO2, RDW, and APSIII, which were closely associated with MDRO infection in ICU sepsis patients. These indicators not only played pivotal roles in the model but also demonstrated significant diagnostic and predictive value in clinical practice. By comprehensively considering these indicators, the model facilitates the accurate identification of high-risk patients, providing a reliable clinical tool for early detection and intervention of infection risks. Furthermore, upon prospective validation in future studies, this model is expected to serve as a robust support tool for individualized medical decision-making—such as enhanced monitoring, targeted prevention, or early tailored treatment for high-risk patients—and for improving patient care.\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003cp\u003eRDW: Red Cell Distribution Width\u003c/p\u003e\n\u003cp\u003eRBC:Red Blood Cell\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eWBC: White Blood Cell\u003c/p\u003e\n\u003cp\u003ePco2: Partial Pressure of Carbon Dioxide\u003c/p\u003e\n\u003cp\u003ePO2: Partial Pressure of Oxygen\u003c/p\u003e\n\u003cp\u003eSOFA: Sequential Organ Failure Assessment\u003c/p\u003e\n\u003cp\u003eAPSIII:Acute physiology score III\u003c/p\u003e\n\u003cp\u003eHTN: Hypertension\u003c/p\u003e\n\u003cp\u003eAKI: Acute Kidney Injury\u003c/p\u003e\n\u003cp\u003eCKD: Chronic Kidney Disease\u003c/p\u003e\n\u003cp\u003eT2DM: Type 2 Diabetes Mellitus.\u003c/p\u003e"},{"header":"Declarations","content":"\u003ch2\u003eFunding\u003c/h2\u003e \u003cp\u003eThis work was supported by grants from the National Natural Science Foundation of China (NSFC), project number 82174312.\u003c/p\u003e\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\u003cp\u003eQianqian Zhang: Methodology, Investigation, Data curation.Nianzhi Zhang: Formal analysis, Data curation.Ying Zheng: Methodology, Formal analysis, Investigation.Jing Zhou: Writing \u0026ndash; review \u0026amp; editing, Supervision, Conceptualization, Funding acquisition.Ling Liu: Writing \u0026ndash; original draft, Conceptualization, Formal analysis.\u003c/p\u003e\u003ch2\u003eData Availability\u003c/h2\u003e\u003cp\u003eThe data are available from the corresponding author upon reasonable request.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003ePiedmont, S. \u003cem\u003eet al.\u003c/em\u003e Sepsis incidence, suspicion, prediction and mortality in emergency medical services: a cohort study related to the current international sepsis guideline. \u003cem\u003eInfection\u003c/em\u003e \u003cstrong\u003e52\u003c/strong\u003e, 1325\u0026ndash;1335 (2024).\u003c/li\u003e\n\u003cli\u003eRhodes, A. \u003cem\u003eet al.\u003c/em\u003e Surviving Sepsis Campaign: International Guidelines for Management of Sepsis and Septic Shock: 2016. \u003cem\u003eIntensive Care Med\u003c/em\u003e \u003cstrong\u003e43\u003c/strong\u003e, 304\u0026ndash;377 (2017).\u003c/li\u003e\n\u003cli\u003eXie, J. \u003cem\u003eet al.\u003c/em\u003e The Epidemiology of Sepsis in Chinese ICUs: A National Cross-Sectional Survey. \u003cem\u003eCrit Care Med\u003c/em\u003e \u003cstrong\u003e48\u003c/strong\u003e, e209\u0026ndash;e218 (2020).\u003c/li\u003e\n\u003cli\u003eYangjia Deng \u003cem\u003eet al.\u003c/em\u003e Consensus among experts in traditional Chinese and Western medicine diagnosis and treatment of severe multidrug-resistant bacterial infections. \u003cem\u003eJournal of Emergency in Traditional Chinese Medicine\u003c/em\u003e \u003cstrong\u003e32\u003c/strong\u003e, 565\u0026ndash;570 (2023).\u003c/li\u003e\n\u003cli\u003eMBBS, N. M., MD, A.-C. U. \u0026amp; MBBS, P. A. Y. P. Multidrug-resistant Gram-negative bacterial infections. \u003cem\u003eThe Lancet\u003c/em\u003e \u003cstrong\u003e405\u003c/strong\u003e, 257\u0026ndash;272 (2025).\u003c/li\u003e\n\u003cli\u003eLiqin Sun \u003cem\u003eet al.\u003c/em\u003e Overview of Resistance Mechanisms and Treatment of Multidrug Resistant Bacteria. \u003cem\u003eChinese Journal of New Clinical Medicine\u003c/em\u003e \u003cstrong\u003e15\u003c/strong\u003e, 921\u0026ndash;927 (2022).\u003c/li\u003e\n\u003cli\u003eSystem C. A. R. S. Report on Multi Drug Resistant Bacteria Monitoring in Traditional Chinese Medicine Hospitals from 2018 to 2021 by the National Bacterial Resistance Monitoring Network. \u003cem\u003eChinese Journal of Infection Control\u003c/em\u003e \u003cstrong\u003e22\u003c/strong\u003e, 1148\u0026ndash;1158 (2023).\u003c/li\u003e\n\u003cli\u003eBusani, S. \u003cem\u003eet al.\u003c/em\u003e Mortality in Patients With Septic Shock by Multidrug Resistant Bacteria: Risk Factors and Impact of Sepsis Treatments. \u003cem\u003eJ Intensive Care Med\u003c/em\u003e \u003cstrong\u003e34\u003c/strong\u003e, 48\u0026ndash;54 (2019).\u003c/li\u003e\n\u003cli\u003eAl-Sunaidar, K. A., Aziz, N. A., Hassan, Y., Jamshed, S. \u0026amp; Sekar, M. Association of Multidrug Resistance Bacteria and Clinical Outcomes of Adult Patients with Sepsis in the Intensive Care Unit. \u003cem\u003eTropical Medicine and Infectious Disease\u003c/em\u003e \u003cstrong\u003e7\u003c/strong\u003e, 365 (2022).\u003c/li\u003e\n\u003cli\u003eChoi, R. Y., Coyner, A. S., Kalpathy-Cramer, J., Chiang, M. F. \u0026amp; Campbell, J. P. Introduction to Machine Learning, Neural Networks, and Deep Learning. \u003cem\u003eTransl Vis Sci Technol\u003c/em\u003e \u003cstrong\u003e9\u003c/strong\u003e, 14 (2020).\u003c/li\u003e\n\u003cli\u003eDong, J. \u003cem\u003eet al.\u003c/em\u003e Machine learning model for early prediction of acute kidney injury (AKI) in pediatric critical care. \u003cem\u003eCrit Care\u003c/em\u003e \u003cstrong\u003e25\u003c/strong\u003e, 288 (2021).\u003c/li\u003e\n\u003cli\u003eGuan, C. \u003cem\u003eet al.\u003c/em\u003e Interpretable machine learning model for new-onset atrial fibrillation prediction in critically ill patients: a multi-center study. \u003cem\u003eCrit Care\u003c/em\u003e \u003cstrong\u003e28\u003c/strong\u003e, 349 (2024).\u003c/li\u003e\n\u003cli\u003eHeo, J. \u003cem\u003eet al.\u003c/em\u003e Machine Learning-Based Model for Prediction of Outcomes in Acute Stroke. \u003cem\u003eStroke\u003c/em\u003e \u003cstrong\u003e50\u003c/strong\u003e, 1263\u0026ndash;1265 (2019).\u003c/li\u003e\n\u003cli\u003eSaliba, J. G. \u003cem\u003eet al.\u003c/em\u003e Enhanced diagnosis of multi-drug-resistant microbes using group association modeling and machine learning. \u003cem\u003eNature Communications\u003c/em\u003e \u003cstrong\u003e16\u003c/strong\u003e, (2025).\u003c/li\u003e\n\u003cli\u003eChiu, L.-W. \u003cem\u003eet al.\u003c/em\u003e Machine learning algorithms to predict colistin-induced nephrotoxicity from electronic health records in patients with multidrug-resistant Gram-negative infection. \u003cem\u003eInternational Journal of Antimicrobial Agents\u003c/em\u003e \u003cstrong\u003e64\u003c/strong\u003e, 107175 (2024).\u003c/li\u003e\n\u003cli\u003eLundberg, S. M. \u003cem\u003eet al.\u003c/em\u003e From Local Explanations to Global Understanding with Explainable AI for Trees. \u003cem\u003eNat Mach Intell\u003c/em\u003e \u003cstrong\u003e2\u003c/strong\u003e, 56\u0026ndash;67 (2020).\u003c/li\u003e\n\u003cli\u003ePetch, J., Di, S. \u0026amp; Nelson, W. Opening the Black Box: The Promise and Limitations of Explainable Machine Learning in Cardiology. \u003cem\u003eCan J Cardiol\u003c/em\u003e \u003cstrong\u003e38\u003c/strong\u003e, 204\u0026ndash;213 (2022).\u003c/li\u003e\n\u003cli\u003eDecisionLinnc Core Team. DecisionLinnc is a platform that integrates multiple programming language environments and enables data processing, data analysis, and machine learning through a visual interface. Statsape Co.Ltd (2023).\u003c/li\u003e\n\u003cli\u003eOxman, D. \u003cem\u003eet al.\u003c/em\u003e Incidence of Multidrug Resistant Infections in Emergency Department Patients with Suspected Sepsis. \u003cem\u003eThe American Journal of the Medical Sciences\u003c/em\u003e \u003cstrong\u003e360\u003c/strong\u003e, 650\u0026ndash;655 (2020).\u003c/li\u003e\n\u003cli\u003eGonz\u0026aacute;lez-Anleo, C. \u003cem\u003eet al.\u003c/em\u003e Risk factors for multidrug-resistant bacteria in critically ill children and MDR score development. \u003cem\u003eEuropean Journal of Pediatrics\u003c/em\u003e \u003cstrong\u003e183\u003c/strong\u003e, 5255\u0026ndash;5265 (2024).\u003c/li\u003e\n\u003cli\u003eDiseases N. C. F. C. \u0026amp; China T. W. C. O. T. R. O. C. H. A. D. I. Summary of China Cardiovascular Health and Disease Report 2024. \u003cem\u003eChinese Circulation Journal\u003c/em\u003e \u003cstrong\u003e40\u003c/strong\u003e, 521\u0026ndash;559 (2025).\u003c/li\u003e\n\u003cli\u003eMurray, E. C. \u003cem\u003eet al.\u003c/em\u003e Therapeutic targeting of inflammation in hypertension: from novel mechanisms to translational perspective. \u003cem\u003eCardiovasc Res\u003c/em\u003e \u003cstrong\u003e117\u003c/strong\u003e, 2589\u0026ndash;2609 (2021).\u003c/li\u003e\n\u003cli\u003eDouna, H. \u003cem\u003eet al.\u003c/em\u003e B- and T-lymphocyte attenuator stimulation protects against atherosclerosis by regulating follicular B cells. \u003cem\u003eCardiovasc Res\u003c/em\u003e \u003cstrong\u003e116\u003c/strong\u003e, 295\u0026ndash;305 (2020).\u003c/li\u003e\n\u003cli\u003eGuzik, T. J., Nosalski, R., Maffia, P. \u0026amp; Drummond, G. R. Immune and inflammatory mechanisms in hypertension. \u003cem\u003eNature Reviews Cardiology\u003c/em\u003e \u003cstrong\u003e21\u003c/strong\u003e, 396\u0026ndash;416 (2024).\u003c/li\u003e\n\u003cli\u003eGomez, H. \u003cem\u003eet al.\u003c/em\u003e A unified theory of sepsis-induced acute kidney injury: inflammation, microcirculatory dysfunction, bioenergetics, and the tubular cell adaptation to injury. \u003cem\u003eShock\u003c/em\u003e \u003cstrong\u003e41\u003c/strong\u003e, 3\u0026ndash;11 (2014).\u003c/li\u003e\n\u003cli\u003eZarbock, A., Gomez, H. \u0026amp; Kellum, J. A. Sepsis-induced acute kidney injury revisited: pathophysiology, prevention and future therapies. \u003cem\u003eCurr Opin Crit Care\u003c/em\u003e \u003cstrong\u003e20\u003c/strong\u003e, 588\u0026ndash;595 (2014).\u003c/li\u003e\n\u003cli\u003eOweis, A. O., Zeyad, H. N., Alshelleh, S. A. \u0026amp; Alzoubi, K. H. Acute Kidney Injury Among Patients with Multi-Drug Resistant Infection: A Study from Jordan. \u003cem\u003eJournal of Multidisciplinary Healthcare\u003c/em\u003e \u003cstrong\u003eVolume 15\u003c/strong\u003e, 2759\u0026ndash;2766 (2022).\u003c/li\u003e\n\u003cli\u003eThille, A. W. \u003cem\u003eet al.\u003c/em\u003e Effect of Postextubation High-Flow Nasal Oxygen With Noninvasive Ventilation vs High-Flow Nasal Oxygen Alone on Reintubation Among Patients at High Risk of Extubation Failure: A Randomized Clinical Trial. \u003cem\u003eJAMA\u003c/em\u003e \u003cstrong\u003e322\u003c/strong\u003e, 1465\u0026ndash;1475 (2019).\u003c/li\u003e\n\u003cli\u003eRosenberg, K. Lower Reintubation Risk with Noninvasive Ventilation Plus High-Flow Nasal Oxygen. \u003cem\u003eAm J Nurs\u003c/em\u003e \u003cstrong\u003e120\u003c/strong\u003e, 50 (2020).\u003c/li\u003e\n\u003cli\u003eLi, N., Zhou, H. \u0026amp; Tang, Q. Red Blood Cell Distribution Width: A Novel Predictive Indicator for Cardiovascular and Cerebrovascular Diseases. \u003cem\u003eDis Markers\u003c/em\u003e \u003cstrong\u003e2017\u003c/strong\u003e, 7089493 (2017).\u003c/li\u003e\n\u003cli\u003eYčas, J. W. Toward a Blood-Borne Biomarker of Chronic Hypoxemia: Red Cell Distribution Width and Respiratory Disease. \u003cem\u003eAdv Clin Chem\u003c/em\u003e \u003cstrong\u003e82\u003c/strong\u003e, 105\u0026ndash;197 (2017).\u003c/li\u003e\n\u003cli\u003eLu, X. \u003cem\u003eet al.\u003c/em\u003e Prognostic significance of increased preoperative red cell distribution width (RDW) and changes in RDW for colorectal cancer. \u003cem\u003eCancer Med\u003c/em\u003e \u003cstrong\u003e12\u003c/strong\u003e, 13361\u0026ndash;13373 (2023).\u003c/li\u003e\n\u003cli\u003eWu, H. \u003cem\u003eet al.\u003c/em\u003e Diagnostic value of RDW for the prediction of mortality in adult sepsis patients: A systematic review and meta-analysis. \u003cem\u003eFront. Immunol.\u003c/em\u003e \u003cstrong\u003e13\u003c/strong\u003e, (2022).\u003c/li\u003e\n\u003cli\u003eKvacskay, P. \u003cem\u003eet al.\u003c/em\u003e Increase of aerobic glycolysis mediated by activated T helper cells drives synovial fibroblasts towards an inflammatory phenotype: new targets for therapy? \u003cem\u003eArthritis Res Ther\u003c/em\u003e \u003cstrong\u003e23\u003c/strong\u003e, 56 (2021).\u003c/li\u003e\n\u003cli\u003eYue \u003cem\u003eet al.\u003c/em\u003e Machine learning for the prediction of acute kidney injury in patients with sepsis. \u003cem\u003eJournal of Translational Medicine\u003c/em\u003e \u003cstrong\u003e20\u003c/strong\u003e, (2022).\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-8242432/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8242432/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eObjective\u003c/strong\u003e: To construct and compare six machine learning models for identifying high-risk factors of multidrug-resistant organism (MDRO) infection in sepsis patients using the MIMIC-IV (v3.1) database.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMethods\u003c/strong\u003e: We conducted a retrospective cohort study of ICU patients meeting Sepsis 3.0 diagnostic criteria from the MIMIC-IV database. Data underwent preprocessing including missing value handling, constant variable removal, and standardization. Key predictors were selected using LASSO regression and the Boruta algorithm. Six machine learning models (LGBM, RF, CatBoost, GBDT, MLP, KNNC) were developed, with SHAP applied for interpretability. Performance was evaluated via AUC, sensitivity, specificity, F1-score, and accuracy. Decision curve analysis (DCA) and calibration curves assessed clinical utility.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults\u003c/strong\u003e: Among 23,191 patients, 2,806 (12.1%) had MDRO infections. Two-stage feature selection (LASSO + Boruta) identified nine core predictors: age, platelet count, red cell distribution width (RDW), blood glucose, lactic acid, partial pressure of oxygen (PO2), Acute Physiology Score III (APS III), hypertension (HTN), and acute kidney injury (AKI). The LGBM model achieved optimal performance (test AUC = 0.964, accuracy = 0.904, F1-score = 0.925). DCA demonstrated significant net clinical benefit for the LGBM and CatBoost models across thresholds of 0.2–0.6. SHAP analysis revealed HTN and AKI as top risk drivers for MDRO infection, while higher PO2 was the primary protective factor.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusion\u003c/strong\u003e: Machine learning models, particularly LGBM, effectively identify ICU sepsis patients at high risk of MDRO infection. Key clinical features (e.g., HTN, AKI, PO2, RDW, lactic acid, APS III) coupled with SHAP interpretability provide a robust decision-support tool for early risk stratification and antimicrobial stewardship optimization.\u003c/p\u003e","manuscriptTitle":"Machine learning prediction and interpretive analysis of multidrug-resistant microbial infection risk in septicemia patients: A study from the MIMIC-IV database​","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-30 01:18:24","doi":"10.21203/rs.3.rs-8242432/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"331068ca-7184-46c1-bda0-06609d3b23cf","owner":[],"postedDate":"December 30th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":60186278,"name":"Health sciences/Biomarkers"},{"id":60186279,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":60186280,"name":"Health sciences/Diseases"},{"id":60186281,"name":"Health sciences/Health care"},{"id":60186282,"name":"Health sciences/Medical research"},{"id":60186283,"name":"Biological sciences/Microbiology"}],"tags":[],"updatedAt":"2026-01-12T04:39:10+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-30 01:18:24","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8242432","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8242432","identity":"rs-8242432","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}