Machine Learning-Based Prediction of Mortality and Multidrug-Resistant Infection Risks in ICU Patients with Suspected Infection: A Prospective National Multicenter Cohort StudyAuthor information

Machine Learning-Based Prediction of Mortality and Multidrug-Resistant Infection Risks in ICU Patients with Suspected Infection: A Prospective National Multicenter Cohort StudyAuthor information | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Machine Learning-Based Prediction of Mortality and Multidrug-Resistant Infection Risks in ICU Patients with Suspected Infection: A Prospective National Multicenter Cohort StudyAuthor information Shuguang Yang, Yao Sun, Ting Wang, Hua Zhang, Wei Sun, Youzhong An, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7333649/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 20 Dec, 2025 Read the published version in BMC Infectious Diseases → Version 1 posted 15 You are reading this latest preprint version Abstract Background Suspected infection or infection may develop into sepsis or septic shock, leading to high mortality rate of patients admitted to ICU. However, suspected infection has not been fully characterized. We performed prediction models to identify independent risk factors of mortality and multidrug resistance for patients with suspected infection when they admitted to the ICU in mainland China. Methods A prospective analysis of Demographic, physiological and microbiological data were recorded for patients with suspected infection when they admitted to ICU between July 2021 and December 2022 in mainland China. Machine learning algorithms were employed to identify risk factors and create prediction models for mortality and multidrug resistance for patients with suspected infection. AUC were calculated and compared by bootstrap to evaluate prediction models. Results A total of 2963 patients from 67 hospitals in mainland China were enrolled into this study. The most common sites of infection were the lung (79.28%), bloodstream (17.11%) and abdomen (16.54%). The mortality rate was 10.90%. Logistic regression prediction model with AUC value 0.87 was selected and identified surgery ( p < 0.01), APACHE Ⅱ ( p < 0.01), and bloodstream infection ( p < 0.01) were independent risk factors of mortality. Furthermore, logistic regression prediction model exhibited the highest AUC (0.86) for predicting the risk of multidrug-resistant infections and identifying six independent risk factors including APACHE Ⅱ ( p < 0.01), bloodstream infections ( p < 0.01), urinary infections ( p < 0.01), Klebsiella pneumoniae ( p < 0.01), Acinetobacter baumanii ( p < 0.01), and Enterococcus faecium ( p < 0.01). Conclusions The most common infection was pneumonia for patients admitted to ICU in mainland China. By means of machine learning techniques, we selected independent risk factors, as well as evaluated prediction models for the mortality and multidrug resistance of patients with suspected infection when they admitted to ICU. Suspected infection Mortality Multidrug resistance Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Introduction Suspected infections represent the primary reason patients are admitted to the intensive care unit (ICU). Epidemiological and therapeutic studies indicate that severe infections may also develop during hospitalization in ICU[ 1 , 2 ]. Patients are more susceptible to infections while in ICU due to exposure to various invasive procedures—such as intubation, mechanical ventilation, and vascular access—while certain sedative drugs further increase infection risk[ 3 , 4 ]. For ICU patients, infections are associated with elevated costs, morbidity, and mortality[ 5 ]. Antibiotics constitute the most heavily consumed medication in the ICU, reflecting the heightened infection risk from underlying conditions, impaired immunity, and multiple invasive devices[ 6 ]. Studies report that 50–70% of patients acquire infections during their ICU stay and receive antibiotics[ 1 , 5 ]. Determining appropriate antibiotic therapy for ICU patients requires balancing excessively broad against inadequate coverage. Epidemiological research has established correlations between ICU antibiotic consumption and the emergence of resistant strains, noting frequent overprescribing and misprescribing that exacerbate drug-resistant bacterial challenges[ 7 , 8 ]. A study of ICU infections at Ruijin Hospital in Shanghai identified Acinetobacter baumannii, Pseudomonas aeruginosa, Klebsiella pneumoniae, and Staphylococcus aureus as the predominant respiratory tract pathogens, with a marked tendency towards reduced antibiotic susceptibility[ 9 ]. Among mechanically ventilated ICU patients, drug-resistant infection incidence rose from 62.5% in 2018 to 71% in 2022[ 10 ]. Multicentre data on the clinical features and microbiology of infections in adult ICU patients are rare and are often limited to a single region or country. Infections caused by multidrug-resistant bacteria constitute a serious problem for ICU patients worldwide. Therefore, we conducted a national-level observational study to explore the clinical characteristics and outcomes of infections in adult ICU patients in China. Methods Study design and sampling We conducted a prospective analysis of patients admitted to the ICUs between July 2021 and December 2022 across mainland China (Fig. 1 ). Ethical approval was granted by the Peking University People’s Hospital Ethics Committee (no. 2021PHB020-001) and all participating hospitals' ethics committees, with informed consent requirements waived. The study was registered with ClinicalTrials.gov ( https://clinicaltrials.gov/show/NCT04966390 ). The investigation spanned 67 hospitals across 16 provinces in mainland China, intentionally encompassing multiple major regions without sampling procedures. Patients The sample consisted of patients with infection, which was defined as the combination of antibiotics (oral or parenteral) and body fluid cultures (blood, urine, cerebrospinal fluid, etc.) within a specific time period[ 11 ]. For example, the antibiotic was administered first and the culture sampling was obtained within 24 hours; however, if culture sampling was performed first, the antibiotic was ordered within 72 hours [ 11 ]. Exclusion criteria were as follows: patients who were not taking antibiotic medication or the duration of taking the medicine was less than three days, patients who were younger than 18 years old, or patient’s clinical data were incomplete. Microbiological testing Specific pathogenic bacteria isolated from clinical specimens—including blood, urine, ascites, and hydrothorax—were identified using standard microbiological methods. Antibiotic susceptibility testing was conducted via the Kirby-Bauer disc diffusion method on Mueller-Hinton agar, in accordance with Clinical and Laboratory Standards Institute guidelines[ 12 ]. All microbiological procedures were performed under quality-controlled conditions. Definitions of infections A sample was considered culture-positive if one or more fluid cultures yielded positive results. Patients could be included more than once in the analysis for distinct infection episodes. Diagnostic criteria for infection types were defined as follows: Pneumonia: require new/progressive pulmonary infiltrates on chest radiography plus ≥ 2 of: (1) Pyrexia (> 38.5°C) or hypothermia ( 37.3°C) or systemic infection signs with ≥ 1 positive blood culture[ 16 ]. Intra-abdominal infection: clinical evidence (abdominal pain/tension) with positive drainage/puncture fluid culture [ 17 ]. Urinary infection: lower urinary symptoms with a quantitative count of ≥ 105 colony forming units of bacteria per millilitre (CFU/ml) and positive urine culture[ 18 ]. Skin/Soft tissue infection: spectrum from mild to life-threatening, diagnosed via positive culture from lesional skin[ 19 ]. Central nervous system infection: classified anatomically (meningitis/encephalitis /myelitis) with positive cerebrospinal fluid culture[ 20 ]. Pelvic infections: uterine/tubal/ovarian infections diagnosed by pelvic pain/effusion with positive pelvic drainage or vaginal/uterine secretion culture[ 21 ]. Patients were assigned to the drug-resistant group if ≥ 1 isolate demonstrated resistance during ICU admission. Drug resistance was defined as non-susceptibility to ≥ 1 antibiotic class, with multidrug-resistant infection indicating non-susceptibility to ≥ 1 agent in ≥ 3 antimicrobial categories [ 22 ]. Data collection Clinical data of patients, including demographic characteristics, underlying medical condition, diagnoses, laboratory examination, imaging diagnosis, inflammatory indicators and microbiological tests were collected via electronic data capture (EDC, https://edc2.cttq.com ). Data on infections and in-hospital mortality were additional recorded. All researchers were well trained in hospitals where standard microbiological methods and antibiotic susceptibility tests could be completed competently. Statistical analysis Statistical analyses were performed using SPSS version 26 (IBM, SPSS Inc, Chicago, USA). Continuous variables with normal distribution were expressed as mean ± standard deviations(SD) and were compared between groups using a two-independent-sample t test. Categorical variables were expressed as percentages (%) and Pearson chi-squared tests were used to compare differences between groups. The level of statistical significance was p < 0.05. Model development Four machine learning algorithms, including logistic regression(LR), random forest(RF), extreme gradient boosting(XGBoost), and gradient boosting machine(GBM) were used to construct the prediction model by using the R software PMS package (version 4.0.3). The first 2074 samples were allocated to the training set, with the subsequent 889 samples forming the validation set. The models were built on the training set and the internal validation set were validated on the best model. The performance of the predictive model was assessed by area under the curve of receiver operating characteristic (AUC). Apply the bootstrap method to calculate the standard error and 95% confidence interval for the AUC (with n = 200 iterations), and perform a comparison of two AUCs. A p value < 0.05 was considered to indicated significance. Results Baseline characteristics A total of 67 hospitals from 16 provinces of China were the sites for the study. Of the 3412 patients with infection, 2963 patients were included in the study (Fig. 1 ). Patients’ characteristics are presented in Additional file Table S1 . The mean score of Acute Physiology and Chronic Health Evaluation Ⅱ(APACHE Ⅱ) was 15.75(range 7 to 37) and the mean age was 64.34 years old (range 18–103 years). The mean length of the ICU stay was 19.02 days. Most patients (27.36%) were from East China (Additional file Figure S1 ), and 92.51% of the patients (n = 2742) were admitted to the ICU at a Grade III hospital (Additional file Figure S2). The largest percentage of ICU patients with an infection were patients with pneumonia (87.19%) followed by bloodstream infection (17.11%) (Additional file Figure S3). Microbiological data were obtained from 11433 samples, including sputum smears, cultures, and next-generation sequencing of blood, urine, cerebrospinal fluid, drainage or puncture fluid, and bronchoalveolar lavage fluid. There were 2194 positive cases among 1661 patients. A total of 1077 cases of Gram-negative bacteria were isolated. Klebsiella pneumoniae was the most frequently isolated among the Gram-negative isolates, and Staphylococcus aureus was the most prevalent Gram-positive isolate (Additional file Figure S4). Fungi were isolated from 253 patients with 55.86% of Candida albicans isolates. Risk factors and prediction model of mortality A total of 323 (10.90%) patients with infection died during their hospital stay. The risk factors for mortality identified by univariate analysis are shown in Table 1 . There were significant differences according to age ( p < 0.01), region of China ( p < 0.01), hospital grades ( p < 0.01), APACHE Ⅱ( p < 0.01), surgery( p < 0.01), hypertension( p < 0.01), CHD( p = 0.01), Cerebrovascular disease( p = 0.01), pneumonia ( p < 0.01), bloodstream infections ( p < 0.01), urinary infections ( p = 0.04), microbiological results (Klebsiella pneumoniae [ p < 0.01], Acinetobacter baumannii [ p < 0.01], Candida albicans [ p < 0.01], and Aspergillus [ p = 0.02]), and multidrug resistant infections ( p < 0.01). Table 1 Basic characteristics of mortality for patients with suspected infection when they admitted to ICU Non-survivors Survivors χ 2 /t p n = 323 n = 2640 Age 68.25 ± 16.63 63.87 ± 15.84 -4.50 < 0.01 Female 105(32.51) 924(35.00) 14.29 0.38 Region 125.47 < 0.01* North China 39(12.07) 741(28.07) East China 63(19.50) 652(24.70) Central China 68(21.05) 589(22.31) Southwest China 130(40.25) 428(16.21) South China 9(2.79) 109(4.13) Northwest China 14(4.33) 90(3.41) Northeast China 0(0.00) 31(1.17) Hospital grades 23.12 < 0.01* Grade ⅢA 306(94.74) 2257(85.49) Grade ⅢB 1(0.31) 118(4.47) Grade ⅢC 3(0.93) 56(2.12) Grade ⅡA 13(4.02) 209(7.92) APACHE Ⅱ a 22.28 ± 4.78 14.96 ± 3.60 -22.63 < 0.01 Surgery 102(31.58) 591(22.39) 13.57 < 0.01 Hypertension 59(18.27) 348(13.18) 6.28 0.01 Diabetes 36(11.15) 209(7.92) 3.96 0.05 CHD b 43(13.31) 237(8.98) 6.32 0.01 Cerebrovascular disease 74(22.91) 349(13.22) 22.08 < 0.01 COPD c 23(7.12) 203(7.69) 0.13 0.72 Immunosuppression 2(0.62) 42(1.59) 1.86 0.17 Pneumonia 283(87.62) 2066(78.26) 15.34 < 0.01 Bloodstream infections 85(26.32) 422(15.98) 21.66 < 0.01 Intro-abdominal infections 57(17.65) 433(16.40) 0.32 0.57 Urinary infections 37(11.46) 213(8.07) 4.27 0.04 Skin infections 10(3.10) 55(2.08) 1.38 0.24 Central system infections 8(2.48) 67(2.54) 0.00 0.95 Pelvic infection 1(0.31) 12(0.45) 0.14 0.71 Klebsiella pneumoniae 62(19.20) 252(9.55) 28.28 < 0.01 Acinetobacter baumanii 52(16.10) 203(7.69) 25.88 < 0.01 Stenotrophomonas maltophilia 8(2.48) 35(1.33) 2.67 0.10 Escherichia coli 16(4.95) 116(4.39) 0.21 0.65 Pseudomonas aeruginosa 20(6.19) 154(5.83) 0.07 0.80 Staphylococcus aureus 4(1.24) 68(2.58) 2.17 0.14 Staphylococcus epidermidis 5(10.53) 28(1.06) 0.62 0.43 Enterococcus faecium 34(1.3) 8(0.30) 2.91 0.09 Candida albicans 23(7.12) 96(3.64) 9.06 < 0.01 Aspergillus 8(2.48) 25(0.95) 6.12 0.02 Virus 1(0.31) 8(0.30) 0.00 0.98 Multidrug resistant infections 106(32.82) 429(16.25) 53.39 < 0.01 ICU LOS d 17.92 ± 32.13 19.17 ± 28.94 0.67 0.50 a APACHE: Acute Physiology and Chronic Health Evaluation, b CHD: Coronary atherosclerotic heart disease, c COPD: Chronic obstructive pulmonary disease, d ICU LOS: Intensive care unit length of stay. * Comparison between two groups, *group and*group. The difference between groups was statistically significant (P < 0.01 or P < 0.05) Four prediction models were conducted by machine learning algorithms based on the aforementioned variables. After removing missing values, the training set contained 2074 samples and the validation set comprised 889 samples for machine learning. The Hosmer-Lemeshow goodness-of-fit test was performed on the validation set, yielding a χ² value of 20.48 ( p = 0.01). ROC analysis using the pROC package demonstrated a training set AUC (equivalent to the C-index) of 0.87 (0.84–0.91). AUC was 0.87(0.83–0.91) in the validation of RF, 0.88(0.84–0.91) in the validation of XGBoost, and 0.87 (0.83–0.91) in the validation of GBM for the prediction model of mortality for ICU patients with suspected sepsis (Fig. 2 ). Bootstrap resampling (n = 200 replicates) was employed to calculate the standard error and 95% confidence interval of the AUC. Additionally, pairwise comparisons of AUCs were performed. A two-sided p -value < 0.05 was considered statistically significant. The analysis revealed no statistically significant differences in AUC between any of prediction models (Table 2 ). Therefore, Three variables including surgery (2.39, 95CI% 1.60–3.56, p < 0.01), APACHE Ⅱ (1.51, 95CI% 1.44–1.58, p < 0.01), and bloodstream infections (2.08, 95CI% 1.40–3.10, p < 0.01) were identified the independent risk factors and a nomogram of mortality for ICU patients with suspected sepsis was performed by LR algorithms (Fig. 3 ). Table 2 Analysis of the differences in AUC values among different machine learning models of mortality Models AUC1 SE1 AUC2 SE2 z p LR * _predvalue VS RF * _predvalue 0.87 0.02 0.87 0.02 -0.08 0.94 LR _predvalue VS GBM * _prevalue 0.87 0.02 0.87 0.02 0.39 0.70 LR _predvalue VS XGB * _prevalue 0.87 0.02 0.88 0.02 -0.59 0.56 RF_predvalue VS GBM_prevalue 0.87 0.02 0.87 0.02 0.59 0.56 RF_predvalue VS XGB_prevalue 0.87 0.019 0.88 0.02 -0.76 0.45 GBM_prevalue VS XGB_prevalue 0.87 0.02 0.88 0.02 -1.43 0.15 *LR: logistic regression, RF: random forest, GMB: gradient boosting machine, XGB: extreme gradient boosting. Table 3 Basic characteristics of multidrug-resistance for patients suspected with infection when they admitted to ICU Multidrug resistance Non-multidrug resistance χ 2 /t p n = 535 n = 2428 Age 67.03 ± 15.226 63.75 ± 16.09 44.31 < 0.01 Female 156(29.16) 873(35.96) 8.93 < 0.01 Region 61.49 < 0.01* North China 81(15.14) 699(28.79) East China 144(26.92) 571(23.52) Central China 127(23.74) 530(21.83) Southwest China 142(26.54) 416(17.13) South China 23(4.30) 95(3.91) Northwest China 18(3.36) 86(3.54) Northeast China 0(0.00) 31(12.76) Hospital grades 17.58 < 0.01* Grade ⅢA 459(85.79) 2104(86.66) Grade ⅢB 11(2.06) 108(4.45) Grade ⅢC 7(1.31) 52(2.14) Grade ⅡA 58(10.84) 164(6.75) APACHE Ⅱ a 16.94 ± 4.97 15.499 ± 4.21 6.95 < 0.01 Surgery 152(28.41) 541(22.28) 9.19 < 0.01 Hypertension 89(16.63) 318(13.10) 4.63 0.03 Diabetes 53(9.91) 192(7.91) 2.31 0.13 CHD b 52(9.72) 228(9.39) 0.06 0.81 Cerebrovascular disease 112(20.93) 311(12.81) 23.65 < 0.01 COPD c 29(5.42) 197(8.11) 4.5 0.03 Immunosuppression 9(1.68) 35(1.44) 0.17 0.68 Pneumonia 477(89.16) 1872(77.10) 38.80 < 0.01 Bloodstream infections 169(31.59) 338(13.92) 96.49 < 0.01 Intro-abdominal infections 87(16.26) 403(16.60) 0.04 0.85 Urinary infections 97(18.13) 153(6.30) 779.41 < 0.01 Skin infections 19(3.55) 46(1.89) 55.61 0.02 Central system infections 26(4.86) 49(2.02) 14.35 < 0.01 Pelvic infection 2(0.37) 11(0.45) 0.06 0.80 Klebsiella pneumoniae 178(33.27) 136(5.60) 354.27 < 0.01 Acinetobacter baumanii 214(40.00) 41(1.69) 818.09 < 0.01 Stenotrophomonas maltophilia 22(4.11) 221(9.10) 32.32 < 0.01 Escherichia coli 62(11.59) 70(2.88) 78.06 < 0.01 Pseudomonas aeruginosa 102(19.07) 72(2.97) 205.58 < 0.01 Staphylococcus aureus 33(6.17) 49(22.01) 9.62 < 0.01 Staphylococcus epidermidis 19(3.55) 14(0.58) 35.23 < 0.01 Enterococcus faecium 30(3.6) 9(0.37) 105.45 < 0.01 Candida albicans 330(5.61) 89(3.67) 4.29 0.04 Aspergillus 6(1.12) 27(1.11) 0.00 0.99 a APACHE: Acute Physiology and Chronic Health Evaluation, b CHD: Coronary atherosclerotic heart disease, c COPD: Chronic obstructive pulmonary disease. * Comparison between two groups, *group and*group. The difference between groups was statistically significant (P < 0.01 or P < 0.05). Infection characteristic, risk factors and prediction model of multidrug resistance Among the infection episodes, the incidence of multidrug resistance was 27.84%, and the incidence of multidrug resistance was 18.06%. There were 23 indictors including age( p < 0.01), female( p < 0.01), region( p < 0.01), hospital grades( p < 0.01), surgery( p < 0.01), APACHE Ⅱ( p < 0.01), hypertension( p = 0.03), Cerebrovascular disease( p < 0.01), COPD( p = 0.03), pneumonia( p < 0.01), bloodstream infections( p < 0.01), urinary infections( p < 0.01), skin infection( p = 0.02), central system infections( p < 0.01), Klebsiella pneumoniae( p < 0.01), Acinetobacter baumanii( p < 0.01), Stenotrophomonas maltophilia( p < 0.01), Escherichia coli( p < 0.01), Pseudomonas aeruginosa( p < 0.01), Staphylococcus aureus( p < 0.01), Staphylococcus epidermidis( p < 0.01), Enterococcus faecium( p < 0.01), and Candida albicans( p = 0.04) by univariate analysis. The training set contained 2074 samples and the validation set comprised 889 samples for machine learning algorithms. In the validation set, AUC value of multidrug resistance was 0.86(0.83–0.90) in LR, 0.86(0.82–0.89) in RF, 0.85(0.81–0.88) in XGBoost, and 0.85(0.82–0.89) in GBM (Fig. 4 ). There were no statistically significant differences in AUC between any of four prediction models (Table 4 ). We selected the LR algorithms for the final model. A nomogram of multidrug resistance for ICU patients with suspected infections was created based on independent risk factors including APACHE Ⅱ (1.06, 95%CI 1.03–1.1, p < 0.01), bloodstream infections (1.82, 95%CI 1.26–2.61, p < 0.01), urinary infections (3.42, 95%CI 2.20–5.30, p < 0.01), Klebsiella pneumoniae (11.67, 95%CI 7.91–17.21, p < 0.01), Acinetobacter baumanii (85.22, 95%CI 50.03-145.18, p < 0.01), and Enterococcus faecium (22.10, 95%CI 8.58–56.93, p < 0.01)(Fig. 5 ). Table 4 Analysis of the differences in AUC values among different machine learning models of multidrug resistance Models AUC1 SE1 AUC2 SE2 z p LR * _predvalue VS RF * _predvalue 0.86 0.02 0.86 0.02 -0.10 0.92 LR_predvalue VS GBM * _prevalue 0.86 0.02 0.85 0.02 1.05 0.29 LR_predvalue VS XGB * _prevalue 0.86 0.02 0.86 0.02 0.32 0.75 RF_predvalue VS GBM_prevalue 0.86 0.015 0.85 0.02 1.04 0.23 RF_predvalue VS XGB_prevalue 0.86 0.02 0.86 0.02 0.43 0.67 GBM_prevalue VS XGB _prevalue 0.85 0.02 0.86 0.02 -1.06 0.29 *LR: logistic regression, RF: random forest, GMB: gradient boosting machine, XGB: extreme gradient boosting. Discussion We conducted a prospective study of infections in patients admitted to the ICU across 16 provinces in China. The results showed that pneumonia and bloodstream infections were the main infections caused by Gram-negative bacteria, especially Klebsiella pneumoniae. We explore the ability of four machine learning algorithms to predict the risk of mortality and multidrug resistance for ICU patients with suspected infections. The final prediction model achieved an AUC value of 0.87 (0.84–0.91) for mortality and 0.86(0.83–0.90) for multidrug resistance based on the logistic regression. Independent risk factors of mortality (surgery, APACHE Ⅱ, and bloodstream infections) and multidrug resistance (APACHE Ⅱ, bloodstream infections, urinary infections, Klebsiella pneumoniae, Acinetobacter baumanii, and Enterococcus faecium) were identified by the logistic regression model. In this study, surgery, APACHE Ⅱ, and bloodstream infections were independent risk factors for mortality of patients with suspected infection when they admitted to ICU. Bloodstream infections with a 30-day mortality rate of 15%, usually develop into severe sepsis, septic shock and multiple organ dysfunction, requiring admission to the ICU[ 23 ]. Previous studies demonstrate that gram-negative bacteria are the most common isolates form bloodstream infections which increased incidence, especially among elderly patients[ 24 ]. Enterococcus species following urinary tract infections, intraabdominal infections, device infections, and endocarditis represent the third leading cause of nosocomial bloodstream infections in the US[ 25 ]. A study focusing on the mortality of critically ill surgical patients found that abdominal infections emerged as the most prevalent site of infection but genitourinary infections correlated with the highest mean lactate and the highest proportion of patients experiencing septic shock[ 26 ]. We found that APACHE Ⅱ, bloodstream infections, urinary infections, Klebsiella pneumoniae, Acinetobacter baumanii, and Enterococcus faecium were independent risk factors of multidrug resistance for patients with suspected infections when they admitted to ICU. According to the US Centers for Disease Control and Prevention, more than 70% of patients receive antibiotics during their stay in the ICU[ 1 ]. Timely and adequate using of antibiotic therapy are an important determinant of survival in critically ill patients in the ICU. Inappropriate antibiotic use leads to infections of multidrug-resistant bacteria that prolong the length of stay and duration of mechanical ventilation[ 27 ]. The prognosis of patients who develop multidrug-resistant infections is poor, which increases the economic burden and mortality rates[ 28 , 29 ]. Klebsiella pneumoniae is the second most common cause of Gram-negative bacteraemia even as an opportunistic pathogen[ 30 ]. Klebsiella pneumoniae causes resistance to many antimicrobials because of their plasmids encoding extended-spectrum beta-lactamases and the acquisition of carbapenemases[ 31 ]. In recent years, artificial intelligence applications have predominantly centered on machine learning methodologies. Contemporary techniques such as neural networks, support vector machines, and random forests have been increasingly utilized to develop predictive models and identify risk factors[ 32 , 33 ]. However, conventional statistical approaches face inherent limitations when processing large volumes of unrefined variables. In our study, logistic regression (LR) was not slightly worse than the other three prediction models. This advantage likely stems from the constrained nature of the characteristics of patients with suspected infection assessment metric. We anticipate machine learning algorithms will emerge as powerful tools for predicting complex clinical outcomes, holding significant promise for future applications. This study also has certain limitations. Firstly, the sample may not be representative of all patients with infection admitted to ICUs in China. Secondly, we did not select overall patient characteristics during the same ICU admission period. We did not know the rate of infection because the data was not complete for all patients. Finally, we validated our models by the same dataset. For example, internal validation cannot detect systematic biases in sampling frameworks. Models may exhibit excellent cross-validation metrics yet fail when applied to populations with divergent feature distributions. However, this is the first study to identify independent risk factors for the mortality and multidrug resistance of patients with suspected infection when they admitted to ICU using a machine learning algorithm and the findings of this study may form the basis for a further investigation in the future. Conclusion In conclusion, pneumonia was the main reason why patients with infection were admitted to the ICU. By means of machine learning techniques, surgery, APACHE Ⅱ, and bloodstream infections were the independent risk factors of the mortality, while APACHE Ⅱ, bloodstream infections, urinary infections, and infected with Klebsiella pneumoniae or Acinetobacter baumanii or Enterococcus faecium were the independent risk factors of multidrug resistance of patients with suspected infection when they admitted to ICU. Abbreviations ICU intensive care unit APACHE Acute Physiology and Chronic Health Evaluation CHD Coronary atherosclerotic heart disease COPD Chronic obstructive pulmonary disease ICU LOS Intensive care unit length of stay DRI Drug Resistant Infection MDR Multidrug Resistant Infection EDC Electronic data capture. LR:logistic regression RF random forest XGBoost extreme gradient boosting GBM gradient boosting machine ROC Receiver Operating Characteristic AUC area under the curve of receiver operating characteristic. Declarations Clinical trial registration Th trial protocol was registered at ClinicalTrials.gov (Identifier: NCT 04966390, Registration Date: July 14, 2021). The full record can be accessed at: https://clinicaltrials.gov/show/NCT04966390 Ethics approval and consent to participate This study was approved by medical ethics committee of Peking University People’s Hospital (2021PHB020-001, Beijing, China). Written informed consent was obtained from all participants prior to the enrollment of this study. Consent publication Not applicable. Competing interests The authors declared no potential conflict of interest concerning the research, authorship, and/or publication of this article. Funding This study was funded by the National Natural Science Foundation of China (grant number 82202366). Author Contribution SY and HZ designed the study. SY and TW participated in the literature search, analysis of data, as well as manuscript writing. YS and WS participated in the literature search and data analysis and YA revised the manuscript. HZ participated in the data analysis and revised the manuscript. HZ had made contributions to the acquisition, analysis of data. HZ and YA are corresponding authors and are responsible for ensuring that all listed authors have approved the manuscript before submission. Acknowledgement Thank you for all patients for their participation in this study and all participants for accomplishing this study. We thank Hua Rong for her electronic information technology. For continuous support, assistance, and cooperation, we thank Chen Li(QiLu Hospital of Shandong University), Li Kong(Affiliated Hospital of Shandong University of Traditional Chinese Medicine), Tingfa Zhou(Lin Yi People’Hospital), Haiming Jiang(The Second of Clinical Medicine of Binzhou Medical university), Xugang Li(Ri Zhao LinYi People’Hospital), Yun Jin(Zi Bo First Hospital), Qiang Sun(Affiliated Hospital of Jining Medical University), Long Qin(Tsinghua University Yuquan Hospital), Qin Dong(The First Affiliated Hospital of Xi’An Jiao Tong University), Xiaochuang Wang(The Second Affiliated Hospital of Xi’An Jiao Tong University), Yong Li(Bao Ji People’s Hospital), Chuan Guo(School of Clinical Medicine& The First Affiliated Hospital of Chengdu Medical College), Xiaobo Huang, Xiaoqin Zhang(Sichuan Academy of Medical Sciences Sichuan Provincial People’s Hospital), Chuan Zhang(Cheng Du third People’s Hospital), Hongde Chen(Cheng Du Tenth People’s Hospital), Yu Du(Sichuan University Fourth Hospital), Hang Xu(The First Affiliated Hospital of ShiHeZi University), Xianying Lei(Affiliated Hospital of Southwest Medical University), Junjing Luo(The First Affiliated Hospital of Xinxiang medical university), Weidong Guo(Xin Xiang Central Hospital), Yinjiang Change(Pu Yang People’s Hospital), Yiyi Sun(He Bi People’s Hospital), Hua Li(The Second Affiliated Hospital of Henan Chinese Medical University), Zhengrong Mao(The First Affiliated Hospital of Henan Chinese Medical University), Li Chen(Affiliated Hospital of North Sichuan Medical College), Faming He(Chest Hospital of Zhengzhou University),Chaogui Zhang(Yi Bin Second People’s Hospital), Yonghui Fan(General Hospital of Pingmei Shenma Group), Jianghua Zhu(The First Affiliated Hospital of Ningbo Hospital),Peili Chen(Shang Qiu First People’s Hospital), Yong Cui(Chongqing University Three Gorges Hospital), Guolong Cai(Zhe Jiang Hospital), Ken Chen(Karamay Central Hospital of Xinjiang), Jian Chen(Affiliated Hospital of Xinjiang Chinese Medical University), Xiangcheng Zhang(Huai An First People’s Hospital), Tianzeng Zhang(An Yang District Hospital), Yuling Liu(Jiaozuo Coal Industry [Group] Co., Ltd. Central Hospital), Chao Jia(Mian Yang Central Hospital), Lifang Wu(Da Feng People’s Hospital), Jiangquan Yu(Northern Jiangsu People’s Hospital), Fang Huang(The First Affiliated Hospital of Soochow University), Yishan Zheng(Nan Jing Sencod Hospital), Xingui Dai(The First Affiliated Hospital of Xiangnan University), Jiangliang Zhou(Huai Hua First People’s Hospital), Xinju Xu(Jiao Zuo Second People’s Hospital), Mingfan Yang(Huo Qiu First People’s Hospital), Liujiu Tian(An Qing First People’s Hospital), Chunli Yang(The First Affiliated Hospital of Nanchang University), Guohui Yang, Jiangquan Fu(Affiliated Hospital of Guizhou Medical University), Donghao Wang(Tianjin Medical University Cancer Institute & Hospital), Youjie Qiao, Jing Wang(Tian Jing People’s Hospital), Bin Chen(The Second Affiliated Hospital of Tianjin Medical University), Baohua Wang, Aiguo Zhang, Yinhua Wang(North China of Science and Technology University Affiliated Hospital), Huisheng Qi(Tangshan Municipal Worker’s Hospital), Hongmei Qin(Yu Lin First People’s Hospital), Baoshan Li(Yun Cheng Central Hospital), Liang Luo(Wu Xi Second People’s Hospital) Jian Luo, Chungen Nie(Ji An People’s Hospital), Shichang Deng, Yonghong Deng(Yu Du People’s Hospital). Data Availability The data are available from the corresponding author on reasonable request. But the datasets are not publicly available due to privacy or ethical restrictions. References Vincent JL, Rello J, Marshall J, Silva E, Anzueto A, Martin CD, Moreno R, Lipman J, Gomersall C, Sakr Y et al : International study of the prevalence and outcomes of infection in intensive care units . Jama 2009, 302 (21):2323-2329. Finfer S, Bellomo R, Lipman J, French C, Dobb G, Myburgh J: Adult-population incidence of severe sepsis in Australian and New Zealand intensive care units . Intensive care medicine 2004, 30 (4):589-596. Hanberger H, Garcia-Rodriguez JA, Gobernado M, Goossens H, Nilsson LE, Struelens MJ: Antibiotic susceptibility among aerobic gram-negative bacilli in intensive care units in 5 European countries. French and Portuguese ICU Study Groups . Jama 1999, 281 (1):67-71. Vincent JL, Bihari DJ, Suter PM, Bruining HA, White J, Nicolas-Chanoin MH, Wolff M, Spencer RC, Hemmer M: The prevalence of nosocomial infection in intensive care units in Europe. Results of the European Prevalence of Infection in Intensive Care (EPIC) Study. EPIC International Advisory Committee . Jama 1995, 274 (8):639-644. Vincent JL, Sakr Y, Sprung CL, Ranieri VM, Reinhart K, Gerlach H, Moreno R, Carlet J, Le Gall JR, Payen D: Sepsis in European intensive care units: results of the SOAP study . Crit Care Med 2006, 34 (2):344-353. Brusselaers N, Vogelaers D, Blot S: The rising problem of antimicrobial resistance in the intensive care unit . Annals of intensive care 2011, 1 :47. Goldmann DA, Weinstein RA, Wenzel RP, Tablan OC, Duma RJ, Gaynes RP, Schlosser J, Martone WJ: Strategies to Prevent and Control the Emergence and Spread of Antimicrobial-Resistant Microorganisms in Hospitals. A challenge to hospital leadership . Jama 1996, 275 (3):234-240. Lipsitch M, Bergstrom CT, Levin BR: The epidemiology of antibiotic resistance in hospitals: paradoxes and prescriptions . Proc Natl Acad Sci U S A 2000, 97 (4):1938-1943. Gupta R, Malik A, Rizvi M, Ahmed M, Singh A: Epidemiology of multidrug-resistant Gram-negative pathogens isolated from ventilator-associated pneumonia in ICU patients . Journal of global antimicrobial resistance 2017, 9 :47-50. Kalın G, Alp E, Chouaikhi A, Roger C: Antimicrobial Multidrug Resistance: Clinical Implications for Infection Management in Critically Ill Patients . Microorganisms 2023, 11 (10). Seymour CW, Liu VX, Iwashyna TJ, Brunkhorst FM, Rea TD, Scherag A, Rubenfeld G, Kahn JM, Shankar-Hari M, Singer M et al : Assessment of Clinical Criteria for Sepsis: For the Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3) . Jama 2016, 315 (8):762-774. Humphries R, Bobenchik AM, Hindler JA, Schuetz AN: Overview of Changes to the Clinical and Laboratory Standards Institute Performance Standards for Antimicrobial Susceptibility Testing, M100, 31st Edition . J Clin Microbiol 2021, 59 (12):e0021321. Koo HJ, Lim S, Choe J, Choi SH, Sung H, Do KH: Radiographic and CT Features of Viral Pneumonia . Radiographics : a review publication of the Radiological Society of North America, Inc 2018, 38 (3):719-739. Almirall J, Serra-Prat M, Bolíbar I, Balasso V: Risk Factors for Community-Acquired Pneumonia in Adults: A Systematic Review of Observational Studies . Respiration; international review of thoracic diseases 2017, 94 (3):299-311. Ottosen J, Evans H: Pneumonia: challenges in the definition, diagnosis, and management of disease . The Surgical clinics of North America 2014, 94 (6):1305-1317. Timsit JF, Ruppé E, Barbier F, Tabah A, Bassetti M: Bloodstream infections in critically ill patients: an expert statement . Intensive care medicine 2020, 46 (2):266-284. Sartelli M, Chichom-Mefire A, Labricciosa FM, Hardcastle T, Abu-Zidan FM, Adesunkanmi AK, Ansaloni L, Bala M, Balogh ZJ, Beltrán MA et al : The management of intra-abdominal infections from a global perspective: 2017 WSES guidelines for management of intra-abdominal infections . World journal of emergency surgery : WJES 2017, 12 :29. Rowe TA, Juthani-Mehta M: Urinary tract infection in older adults . Aging health 2013, 9 (5). Moffarah AS, Al Mohajer M, Hurwitz BL, Armstrong DG: Skin and Soft Tissue Infections . Microbiol Spectr 2016, 4 (4). He T, Kaplan S, Kamboj M, Tang YW: Laboratory Diagnosis of Central Nervous System Infection . Curr Infect Dis Rep 2016, 18 (11):35. Mitchell C, Prabhu M: Pelvic inflammatory disease: current concepts in pathogenesis, diagnosis and treatment . Infect Dis Clin North Am 2013, 27 (4):793-809. Magiorakos AP, Srinivasan A, Carey RB, Carmeli Y, Falagas ME, Giske CG, Harbarth S, Hindler JF, Kahlmeter G, Olsson-Liljequist B et al : Multidrug-resistant, extensively drug-resistant and pandrug-resistant bacteria: an international expert proposal for interim standard definitions for acquired resistance . Clinical microbiology and infection : the official publication of the European Society of Clinical Microbiology and Infectious Diseases 2012, 18 (3):268-281. Laupland KB, Gregson DB, Zygun DA, Doig CJ, Mortis G, Church DL: Severe bloodstream infections: a population-based assessment . Crit Care Med 2004, 32 (4):992-997. Reunes S, Rombaut V, Vogelaers D, Brusselaers N, Lizy C, Cankurtaran M, Labeau S, Petrovic M, Blot S: Risk factors and mortality for nosocomial bloodstream infections in elderly patients . European journal of internal medicine 2011, 22 (5):e39-44. Ike Y: [Pathogenicity of Enterococci] . Nihon saikingaku zasshi Japanese journal of bacteriology 2017, 72 (2):189-211. Bin Ghaffar W, Nazir S, Siddiqui S, Abdul Ghaffar MB, Khan MF, Latif A, Cheema Z, Hanif S, Sohaib M: Association Between the Site of Infection and Mortality Analysis in Critically Ill Surgical Patients . Cureus 2023, 15 (12):e50033. Reacher MH, Shah A, Livermore DM, Wale MC, Graham C, Johnson AP, Heine H, Monnickendam MA, Barker KF, James D et al : Bacteraemia and antibiotic resistance of its pathogens reported in England and Wales between 1990 and 1998: trend analysis . BMJ (Clinical research ed) 2000, 320 (7229):213-216. Siegel JD, Rhinehart E, Jackson M, Chiarello L: Management of multidrug-resistant organisms in health care settings, 2006 . American journal of infection control 2007, 35 (10 Suppl 2):S165-193. Neidell MJ, Cohen B, Furuya Y, Hill J, Jeon CY, Glied S, Larson EL: Costs of healthcare- and community-associated infections with antimicrobial-resistant versus antimicrobial-susceptible organisms . Clinical infectious diseases : an official publication of the Infectious Diseases Society of America 2012, 55 (6):807-815. Cubero M, Grau I, Tubau F, Pallarés R, Domínguez M, Liñares J, Ardanuy C: Molecular Epidemiology of Klebsiella pneumoniae Strains Causing Bloodstream Infections in Adults . Microbial drug resistance (Larchmont, NY) 2018, 24 (7):949-957. Paramythiotou E, Routsi C: Association between infections caused by multidrug-resistant gram-negative bacteria and mortality in critically ill patients . World journal of critical care medicine 2016, 5 (2):111-120. Desai RJ, Wang SV, Vaduganathan M, Evers T, Schneeweiss S: Comparison of Machine Learning Methods With Traditional Models for Use of Administrative Claims With Electronic Medical Records to Predict Heart Failure Outcomes . JAMA network open 2020, 3 (1):e1918962. Mortazavi BJ, Bucholz EM, Desai NR, Huang C, Curtis JP, Masoudi FA, Shaw RE, Negahban SN, Krumholz HM: Comparison of Machine Learning Methods With National Cardiovascular Data Registry Models for Prediction of Risk of Bleeding After Percutaneous Coronary Intervention . JAMA network open 2019, 2 (7):e196835. Additional Declarations No competing interests reported. Supplementary Files Additionalfile.docx Cite Share Download PDF Status: Published Journal Publication published 20 Dec, 2025 Read the published version in BMC Infectious Diseases → Version 1 posted Editorial decision: Revision requested 06 Oct, 2025 Reviews received at journal 04 Oct, 2025 Reviews received at journal 04 Oct, 2025 Reviewers agreed at journal 25 Sep, 2025 Reviewers agreed at journal 24 Sep, 2025 Reviews received at journal 24 Sep, 2025 Reviewers agreed at journal 24 Sep, 2025 Reviewers agreed at journal 22 Sep, 2025 Reviews received at journal 22 Sep, 2025 Reviewers agreed at journal 12 Sep, 2025 Reviewers invited by journal 09 Sep, 2025 Editor invited by journal 20 Aug, 2025 Editor assigned by journal 17 Aug, 2025 Submission checks completed at journal 17 Aug, 2025 First submitted to journal 09 Aug, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7333649","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":515276730,"identity":"274428eb-011e-4a4a-9d58-fcff3049e3ba","order_by":0,"name":"Shuguang Yang","email":"","orcid":"","institution":"Peking University People’s Hospital","correspondingAuthor":false,"prefix":"","firstName":"Shuguang","middleName":"","lastName":"Yang","suffix":""},{"id":515276731,"identity":"905e758e-6c9c-4d25-8dae-1cb4b1d2b458","order_by":1,"name":"Yao Sun","email":"","orcid":"","institution":"Peking University People’s Hospital","correspondingAuthor":false,"prefix":"","firstName":"Yao","middleName":"","lastName":"Sun","suffix":""},{"id":515276732,"identity":"b3454e02-5889-4b41-966e-c3c9bd05b09a","order_by":2,"name":"Ting Wang","email":"","orcid":"","institution":"Peking University People’s Hospital","correspondingAuthor":false,"prefix":"","firstName":"Ting","middleName":"","lastName":"Wang","suffix":""},{"id":515276733,"identity":"f3419fd7-9655-47e1-8bc8-9c41e82aa45d","order_by":3,"name":"Hua Zhang","email":"","orcid":"","institution":"Peking University Third Hospital","correspondingAuthor":false,"prefix":"","firstName":"Hua","middleName":"","lastName":"Zhang","suffix":""},{"id":515276734,"identity":"3f47f28c-7669-4579-becc-ae7bc048dc30","order_by":4,"name":"Wei Sun","email":"","orcid":"","institution":"Peking University International Hospital","correspondingAuthor":false,"prefix":"","firstName":"Wei","middleName":"","lastName":"Sun","suffix":""},{"id":515276735,"identity":"2b1c8694-a1fb-41ae-9d22-7c1657bb924e","order_by":5,"name":"Youzhong An","email":"","orcid":"","institution":"Peking University People’s Hospital","correspondingAuthor":false,"prefix":"","firstName":"Youzhong","middleName":"","lastName":"An","suffix":""},{"id":515276736,"identity":"767b6632-32af-411f-bd20-7bdb83b68420","order_by":6,"name":"Huiying Zhao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8klEQVRIiWNgGAWjYDACCQYGZhDJxsDA+IDhAEgogXgtzAakaAEDNgmitMjPbn74uLDNIrFPuv1adcGZwwz87DkGDD934NbCOOeYsfHMNonENpkzZbdn3DjMINnzxoCx9wxuLcwSCWbSvCAtEjlpt3k+HGYwuJFjwMzYhlsLm0T6N7iWYpAWe0JaeCRyYLakH2PmATrMQIKAFgmJnGJjnnMSxkBbmKVnnEnnkTjzrOBgLx4t8jPSNz7mKauTnT8j/eHngmPWcvztyRsf/MSjBQYcGxh4DEARxAPiHSCsgYHBnoGB/QEzQWWjYBSMglEwIgEA6jtMpT4aHToAAAAASUVORK5CYII=","orcid":"","institution":"Peking University People’s Hospital","correspondingAuthor":true,"prefix":"","firstName":"Huiying","middleName":"","lastName":"Zhao","suffix":""}],"badges":[],"createdAt":"2025-08-09 11:38:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7333649/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7333649/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s12879-025-12354-8","type":"published","date":"2025-12-20T15:57:07+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":91527728,"identity":"873ab4f1-da47-448c-9028-ca7555e6b42b","added_by":"auto","created_at":"2025-09-17 11:22:02","extension":"jpg","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":218284,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eFlow chart of hospital recruitment and patient enrollment. Provinces in mainland China were divided into seven geographical regions. A total of 2963 patients from 67 hospitals were included in this study\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"Figure1.tif.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7333649/v1/2cb7f4a87310c08730a8dfdc.jpg"},{"id":91525320,"identity":"30026eb4-e7ac-4482-86b6-3376a025e8bb","added_by":"auto","created_at":"2025-09-17 11:06:02","extension":"jpg","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":122933,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eReceiver operating characteristic (ROC) curves of the prediction model for mortality of patients with suspected infection conducted by machine learning algorithms\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"Figure2.tif.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7333649/v1/a3ec271ce096b2436c9b18f4.jpg"},{"id":91525318,"identity":"60c0fd52-5d9a-45a7-9af4-bc8d351f4c2e","added_by":"auto","created_at":"2025-09-17 11:06:02","extension":"jpg","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":49266,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eNomogram for mortality. To estimate the probability of moratlity, mark patient value at each axis, draw a straight line perpendicular to the point axis, and calculate the points for all variables. Then mark the sum on the total point axis and the points met the risk axis\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"Figure3.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7333649/v1/51d36a1064b928f36dd30cf7.jpg"},{"id":91525322,"identity":"74ad6e66-9c1d-45b7-a14b-c6b5c8f806c0","added_by":"auto","created_at":"2025-09-17 11:06:02","extension":"jpg","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":115582,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eReceiver operating characteristic (ROC) curves of the prediction model for multidrug resistance of patients with suspected infection conducted by machine learning algorithms\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"Figure4.tif.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7333649/v1/5e8ace34d345aa602d484aa9.jpg"},{"id":91527133,"identity":"22fe6903-183e-473e-8e70-b49c39569cbf","added_by":"auto","created_at":"2025-09-17 11:14:02","extension":"jpg","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":152554,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eNomogram for multidrug resistance. The value of variable was given a score on the point scale axis. To estimate the risk of the time of first postoperative defecation, a total score could be calculated by each axis and could be projected to the lower total point scale\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"Figure5.tif.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7333649/v1/cd766382b73fc7592c291838.jpg"},{"id":98813871,"identity":"4336a55f-7a23-49c7-a230-52ef2e2e2bb2","added_by":"auto","created_at":"2025-12-22 16:06:32","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3651697,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7333649/v1/c1aec6e7-4817-414f-bfb3-0d2002f68295.pdf"},{"id":91525315,"identity":"f8ab29db-7a14-4876-b3ce-42ed44a29c64","added_by":"auto","created_at":"2025-09-17 11:06:02","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":42459,"visible":true,"origin":"","legend":"","description":"","filename":"Additionalfile.docx","url":"https://assets-eu.researchsquare.com/files/rs-7333649/v1/833b5aec72825f3f4af12a93.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Machine Learning-Based Prediction of Mortality and Multidrug-Resistant Infection Risks in ICU Patients with Suspected Infection: A Prospective National Multicenter Cohort StudyAuthor information","fulltext":[{"header":"Introduction","content":"\u003cp\u003eSuspected infections represent the primary reason patients are admitted to the intensive care unit (ICU). Epidemiological and therapeutic studies indicate that severe infections may also develop during hospitalization in ICU[\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e, \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. Patients are more susceptible to infections while in ICU due to exposure to various invasive procedures\u0026mdash;such as intubation, mechanical ventilation, and vascular access\u0026mdash;while certain sedative drugs further increase infection risk[\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e, \u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. For ICU patients, infections are associated with elevated costs, morbidity, and mortality[\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eAntibiotics constitute the most heavily consumed medication in the ICU, reflecting the heightened infection risk from underlying conditions, impaired immunity, and multiple invasive devices[\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. Studies report that 50\u0026ndash;70% of patients acquire infections during their ICU stay and receive antibiotics[\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e, \u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]. Determining appropriate antibiotic therapy for ICU patients requires balancing excessively broad against inadequate coverage. Epidemiological research has established correlations between ICU antibiotic consumption and the emergence of resistant strains, noting frequent overprescribing and misprescribing that exacerbate drug-resistant bacterial challenges[\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e, \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. A study of ICU infections at Ruijin Hospital in Shanghai identified Acinetobacter baumannii, Pseudomonas aeruginosa, Klebsiella pneumoniae, and Staphylococcus aureus as the predominant respiratory tract pathogens, with a marked tendency towards reduced antibiotic susceptibility[\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]. Among mechanically ventilated ICU patients, drug-resistant infection incidence rose from 62.5% in 2018 to 71% in 2022[\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eMulticentre data on the clinical features and microbiology of infections in adult ICU patients are rare and are often limited to a single region or country. Infections caused by multidrug-resistant bacteria constitute a serious problem for ICU patients worldwide. Therefore, we conducted a national-level observational study to explore the clinical characteristics and outcomes of infections in adult ICU patients in China.\u003c/p\u003e"},{"header":"Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\u003ch2\u003eStudy design and sampling\u003c/h2\u003e\u003cp\u003eWe conducted a prospective analysis of patients admitted to the ICUs between July 2021 and December 2022 across mainland China (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e). Ethical approval was granted by the Peking University People\u0026rsquo;s Hospital Ethics Committee (no. 2021PHB020-001) and all participating hospitals' ethics committees, with informed consent requirements waived. The study was registered with ClinicalTrials.gov (\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://clinicaltrials.gov/show/NCT04966390\u003c/span\u003e\u003cspan address=\"https://clinicaltrials.gov/show/NCT04966390\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e). The investigation spanned 67 hospitals across 16 provinces in mainland China, intentionally encompassing multiple major regions without sampling procedures.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\n\u003ch3\u003ePatients\u003c/h3\u003e\n\u003cp\u003eThe sample consisted of patients with infection, which was defined as the combination of antibiotics (oral or parenteral) and body fluid cultures (blood, urine, cerebrospinal fluid, etc.) within a specific time period[\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e]. For example, the antibiotic was administered first and the culture sampling was obtained within 24 hours; however, if culture sampling was performed first, the antibiotic was ordered within 72 hours [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eExclusion criteria were as follows: patients who were not taking antibiotic medication or the duration of taking the medicine was less than three days, patients who were younger than 18 years old, or patient\u0026rsquo;s clinical data were incomplete.\u003c/p\u003e\n\u003ch3\u003eMicrobiological testing\u003c/h3\u003e\n\u003cp\u003eSpecific pathogenic bacteria isolated from clinical specimens\u0026mdash;including blood, urine, ascites, and hydrothorax\u0026mdash;were identified using standard microbiological methods. Antibiotic susceptibility testing was conducted via the Kirby-Bauer disc diffusion method on Mueller-Hinton agar, in accordance with Clinical and Laboratory Standards Institute guidelines[\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e]. All microbiological procedures were performed under quality-controlled conditions.\u003c/p\u003e\n\u003ch3\u003eDefinitions of infections\u003c/h3\u003e\n\u003cp\u003eA sample was considered culture-positive if one or more fluid cultures yielded positive results. Patients could be included more than once in the analysis for distinct infection episodes. Diagnostic criteria for infection types were defined as follows:\u003c/p\u003e\u003cp\u003ePneumonia: require new/progressive pulmonary infiltrates on chest radiography plus\u0026thinsp;\u0026ge;\u0026thinsp;2 of: (1) Pyrexia (\u0026gt;\u0026thinsp;38.5\u0026deg;C) or hypothermia (\u0026lt;\u0026thinsp;36\u0026deg;C), (2) Positive tracheobronchial/BAL culture or significant bacteriological counts in respiratory secretions, (3) leucocytosis\u0026thinsp;\u0026ge;\u0026thinsp;12\u0026times;10\u003csup\u003e9\u003c/sup\u003e/L[\u003cspan additionalcitationids=\"CR14\" citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eBloodstream infection: pyrexia (\u0026gt;\u0026thinsp;37.3\u0026deg;C) or systemic infection signs with \u0026ge;\u0026thinsp;1 positive blood culture[\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eIntra-abdominal infection: clinical evidence (abdominal pain/tension) with positive drainage/puncture fluid culture [\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eUrinary infection: lower urinary symptoms with a quantitative count of \u0026ge;\u0026thinsp;105 colony forming units of bacteria per millilitre (CFU/ml) and positive urine culture[\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eSkin/Soft tissue infection: spectrum from mild to life-threatening, diagnosed via positive culture from lesional skin[\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eCentral nervous system infection: classified anatomically (meningitis/encephalitis /myelitis) with positive cerebrospinal fluid culture[\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e].\u003c/p\u003e\u003cp\u003ePelvic infections: uterine/tubal/ovarian infections diagnosed by pelvic pain/effusion with positive pelvic drainage or vaginal/uterine secretion culture[\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e].\u003c/p\u003e\u003cp\u003ePatients were assigned to the drug-resistant group if\u0026thinsp;\u0026ge;\u0026thinsp;1 isolate demonstrated resistance during ICU admission. Drug resistance was defined as non-susceptibility to \u0026ge;\u0026thinsp;1 antibiotic class, with multidrug-resistant infection indicating non-susceptibility to \u0026ge;\u0026thinsp;1 agent in \u0026ge;\u0026thinsp;3 antimicrobial categories [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e].\u003c/p\u003e\n\u003ch3\u003eData collection\u003c/h3\u003e\n\u003cp\u003eClinical data of patients, including demographic characteristics, underlying medical condition, diagnoses, laboratory examination, imaging diagnosis, inflammatory indicators and microbiological tests were collected via electronic data capture (EDC, \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://edc2.cttq.com\u003c/span\u003e\u003cspan address=\"https://edc2.cttq.com\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e). Data on infections and in-hospital mortality were additional recorded. All researchers were well trained in hospitals where standard microbiological methods and antibiotic susceptibility tests could be completed competently.\u003c/p\u003e\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e\u003ch2\u003eStatistical analysis\u003c/h2\u003e\u003cp\u003eStatistical analyses were performed using SPSS version 26 (IBM, SPSS Inc, Chicago, USA). Continuous variables with normal distribution were expressed as mean\u0026thinsp;\u0026plusmn;\u0026thinsp;standard deviations(SD) and were compared between groups using a two-independent-sample \u003cem\u003et\u003c/em\u003e test. Categorical variables were expressed as percentages (%) and Pearson chi-squared tests were used to compare differences between groups. The level of statistical significance was \u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05.\u003c/p\u003e\u003c/div\u003e\n\u003ch3\u003eModel development\u003c/h3\u003e\n\u003cp\u003eFour machine learning algorithms, including logistic regression(LR), random forest(RF), extreme gradient boosting(XGBoost), and gradient boosting machine(GBM) were used to construct the prediction model by using the R software PMS package (version 4.0.3). The first 2074 samples were allocated to the training set, with the subsequent 889 samples forming the validation set. The models were built on the training set and the internal validation set were validated on the best model. The performance of the predictive model was assessed by area under the curve of receiver operating characteristic (AUC). Apply the bootstrap method to calculate the standard error and 95% confidence interval for the AUC (with n\u0026thinsp;=\u0026thinsp;200 iterations), and perform a comparison of two AUCs. A \u003cem\u003ep\u003c/em\u003e value\u0026thinsp;\u0026lt;\u0026thinsp;0.05 was considered to indicated significance.\u003c/p\u003e"},{"header":"Results","content":"\u003cdiv id=\"Sec11\" class=\"Section2\"\u003e\u003ch2\u003eBaseline characteristics\u003c/h2\u003e\u003cp\u003eA total of 67 hospitals from 16 provinces of China were the sites for the study. Of the 3412 patients with infection, 2963 patients were included in the study (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e). Patients\u0026rsquo; characteristics are presented in Additional file Table \u003cspan refid=\"MOESM1\" class=\"InternalRef\"\u003eS1\u003c/span\u003e. The mean score of Acute Physiology and Chronic Health Evaluation Ⅱ(APACHE Ⅱ) was 15.75(range 7 to 37) and the mean age was 64.34 years old (range 18\u0026ndash;103 years). The mean length of the ICU stay was 19.02 days. Most patients (27.36%) were from East China (Additional file Figure \u003cspan refid=\"MOESM1\" class=\"InternalRef\"\u003eS1\u003c/span\u003e), and 92.51% of the patients (n\u0026thinsp;=\u0026thinsp;2742) were admitted to the ICU at a Grade III hospital (Additional file Figure S2). The largest percentage of ICU patients with an infection were patients with pneumonia (87.19%) followed by bloodstream infection (17.11%) (Additional file Figure S3).\u003c/p\u003e\u003cp\u003eMicrobiological data were obtained from 11433 samples, including sputum smears, cultures, and next-generation sequencing of blood, urine, cerebrospinal fluid, drainage or puncture fluid, and bronchoalveolar lavage fluid. There were 2194 positive cases among 1661 patients. A total of 1077 cases of Gram-negative bacteria were isolated. Klebsiella pneumoniae was the most frequently isolated among the Gram-negative isolates, and Staphylococcus aureus was the most prevalent Gram-positive isolate (Additional file Figure S4). Fungi were isolated from 253 patients with 55.86% of Candida albicans isolates.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec12\" class=\"Section2\"\u003e\u003ch2\u003eRisk factors and prediction model of mortality\u003c/h2\u003e\u003cp\u003eA total of 323 (10.90%) patients with infection died during their hospital stay. The risk factors for mortality identified by univariate analysis are shown in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e. There were significant differences according to age (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), region of China (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), hospital grades (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), APACHE Ⅱ(\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), surgery(\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), hypertension(\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), CHD(\u003cem\u003ep\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.01), Cerebrovascular disease(\u003cem\u003ep\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.01), pneumonia (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), bloodstream infections (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), urinary infections (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.04), microbiological results (Klebsiella pneumoniae [\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01], Acinetobacter baumannii [\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01], Candida albicans [\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01], and Aspergillus [\u003cem\u003ep\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.02]), and multidrug resistant infections (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01).\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eBasic characteristics of mortality for patients with suspected infection when they admitted to ICU\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"5\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eNon-survivors\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eSurvivors\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003eχ\u003csup\u003e2\u003c/sup\u003e/t\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003en\u0026thinsp;=\u0026thinsp;323\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003en\u0026thinsp;=\u0026thinsp;2640\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAge\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e68.25\u0026thinsp;\u0026plusmn;\u0026thinsp;16.63\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e63.87\u0026thinsp;\u0026plusmn;\u0026thinsp;15.84\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e-4.50\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eFemale\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e105(32.51)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e924(35.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e14.29\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.38\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRegion\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e125.47\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01*\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNorth China\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e39(12.07)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e741(28.07)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eEast China\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e63(19.50)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e652(24.70)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCentral China\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e68(21.05)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e589(22.31)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSouthwest China\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e130(40.25)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e428(16.21)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSouth China\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e9(2.79)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e109(4.13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNorthwest China\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e14(4.33)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e90(3.41)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNortheast China\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0(0.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e31(1.17)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHospital grades\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e23.12\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01*\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGrade ⅢA\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e306(94.74)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e2257(85.49)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGrade ⅢB\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1(0.31)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e118(4.47)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGrade ⅢC\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e3(0.93)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e56(2.12)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGrade ⅡA\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e13(4.02)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e209(7.92)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAPACHE Ⅱ\u003csup\u003ea\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e22.28\u0026thinsp;\u0026plusmn;\u0026thinsp;4.78\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e14.96\u0026thinsp;\u0026plusmn;\u0026thinsp;3.60\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e-22.63\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSurgery\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e102(31.58)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e591(22.39)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e13.57\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHypertension\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e59(18.27)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e348(13.18)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e6.28\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eDiabetes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e36(11.15)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e209(7.92)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e3.96\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.05\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCHD\u003csup\u003eb\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e43(13.31)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e237(8.98)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e6.32\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCerebrovascular disease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e74(22.91)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e349(13.22)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e22.08\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCOPD\u003csup\u003ec\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e23(7.12)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e203(7.69)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.13\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.72\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eImmunosuppression\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2(0.62)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e42(1.59)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e1.86\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.17\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePneumonia\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e283(87.62)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e2066(78.26)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e15.34\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBloodstream infections\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e85(26.32)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e422(15.98)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e21.66\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eIntro-abdominal infections\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e57(17.65)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e433(16.40)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.32\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.57\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eUrinary infections\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e37(11.46)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e213(8.07)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e4.27\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.04\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSkin infections\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e10(3.10)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e55(2.08)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e1.38\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.24\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCentral system infections\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e8(2.48)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e67(2.54)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.00\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.95\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePelvic infection\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1(0.31)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e12(0.45)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.14\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.71\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eKlebsiella pneumoniae\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e62(19.20)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e252(9.55)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e28.28\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAcinetobacter baumanii\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e52(16.10)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e203(7.69)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e25.88\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eStenotrophomonas maltophilia\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e8(2.48)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e35(1.33)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e2.67\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.10\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eEscherichia coli\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e16(4.95)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e116(4.39)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.21\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.65\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePseudomonas aeruginosa\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e20(6.19)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e154(5.83)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.07\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.80\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eStaphylococcus aureus\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e4(1.24)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e68(2.58)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e2.17\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.14\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eStaphylococcus epidermidis\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e5(10.53)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e28(1.06)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.62\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.43\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eEnterococcus faecium\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e34(1.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e8(0.30)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e2.91\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.09\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCandida albicans\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e23(7.12)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e96(3.64)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e9.06\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAspergillus\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e8(2.48)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e25(0.95)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e6.12\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eVirus\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1(0.31)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e8(0.30)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.00\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.98\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMultidrug resistant infections\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e106(32.82)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e429(16.25)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e53.39\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eICU LOS\u003csup\u003ed\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e17.92\u0026thinsp;\u0026plusmn;\u0026thinsp;32.13\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e19.17\u0026thinsp;\u0026plusmn;\u0026thinsp;28.94\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.67\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.50\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"5\"\u003e\u003csup\u003ea\u003c/sup\u003eAPACHE: Acute Physiology and Chronic Health Evaluation, \u003csup\u003eb\u003c/sup\u003eCHD: Coronary atherosclerotic heart disease, \u003csup\u003ec\u003c/sup\u003eCOPD: Chronic obstructive pulmonary disease, \u003csup\u003ed\u003c/sup\u003eICU LOS: Intensive care unit length of stay. * Comparison between two groups, *group and*group. The difference between groups was statistically significant (P\u0026thinsp;\u0026lt;\u0026thinsp;0.01 or P\u0026thinsp;\u0026lt;\u0026thinsp;0.05)\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003eFour prediction models were conducted by machine learning algorithms based on the aforementioned variables. After removing missing values, the training set contained 2074 samples and the validation set comprised 889 samples for machine learning. The Hosmer-Lemeshow goodness-of-fit test was performed on the validation set, yielding a χ\u0026sup2; value of 20.48 (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.01). ROC analysis using the pROC package demonstrated a training set AUC (equivalent to the C-index) of 0.87 (0.84\u0026ndash;0.91). AUC was 0.87(0.83\u0026ndash;0.91) in the validation of RF, 0.88(0.84\u0026ndash;0.91) in the validation of XGBoost, and 0.87 (0.83\u0026ndash;0.91) in the validation of GBM for the prediction model of mortality for ICU patients with suspected sepsis (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e). Bootstrap resampling (n\u0026thinsp;=\u0026thinsp;200 replicates) was employed to calculate the standard error and 95% confidence interval of the AUC. Additionally, pairwise comparisons of AUCs were performed. A two-sided \u003cem\u003ep\u003c/em\u003e-value\u0026thinsp;\u0026lt;\u0026thinsp;0.05 was considered statistically significant. The analysis revealed no statistically significant differences in AUC between any of prediction models (Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e). Therefore, Three variables including surgery (2.39, 95CI% 1.60\u0026ndash;3.56, \u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), APACHE Ⅱ (1.51, 95CI% 1.44\u0026ndash;1.58, \u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), and bloodstream infections (2.08, 95CI% 1.40\u0026ndash;3.10, \u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01) were identified the independent risk factors and a nomogram of mortality for ICU patients with suspected sepsis was performed by LR algorithms (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e).\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eAnalysis of the differences in AUC values among different machine learning models of mortality\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"7\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eModels\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eAUC1\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eSE1\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eAUC2\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eSE2\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003ez\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLR\u003csup\u003e*\u003c/sup\u003e_predvalue VS RF\u003csup\u003e*\u003c/sup\u003e_predvalue\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.87\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.87\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e-0.08\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.94\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLR _predvalue VS GBM\u003csup\u003e*\u003c/sup\u003e_prevalue\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.87\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.87\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.39\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.70\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLR _predvalue VS XGB\u003csup\u003e*\u003c/sup\u003e_prevalue\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.87\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.88\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e-0.59\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.56\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRF_predvalue VS GBM_prevalue\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.87\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.87\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.59\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.56\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRF_predvalue VS XGB_prevalue\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.87\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.019\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.88\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e-0.76\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.45\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGBM_prevalue VS XGB_prevalue\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.87\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.88\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e-1.43\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.15\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"7\"\u003e*LR: logistic regression, RF: random forest, GMB: gradient boosting machine, XGB: extreme gradient boosting.\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003e\u003cb\u003eBasic characteristics of multidrug-resistance for patients suspected with infection when they admitted to ICU\u003c/b\u003e\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"5\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eMultidrug resistance\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eNon-multidrug resistance\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003eχ\u003csup\u003e2\u003c/sup\u003e/t\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003en\u0026thinsp;=\u0026thinsp;535\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003en\u0026thinsp;=\u0026thinsp;2428\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAge\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e67.03\u0026thinsp;\u0026plusmn;\u0026thinsp;15.226\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e63.75\u0026thinsp;\u0026plusmn;\u0026thinsp;16.09\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e44.31\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eFemale\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e156(29.16)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e873(35.96)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e8.93\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRegion\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e61.49\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01*\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNorth China\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e81(15.14)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e699(28.79)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eEast China\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e144(26.92)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e571(23.52)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCentral China\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e127(23.74)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e530(21.83)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSouthwest China\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e142(26.54)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e416(17.13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSouth China\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e23(4.30)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e95(3.91)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNorthwest China\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e18(3.36)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e86(3.54)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNortheast China\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0(0.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e31(12.76)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHospital grades\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e17.58\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01*\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGrade ⅢA\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e459(85.79)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e2104(86.66)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGrade ⅢB\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e11(2.06)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e108(4.45)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGrade ⅢC\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e7(1.31)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e52(2.14)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGrade ⅡA\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e58(10.84)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e164(6.75)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAPACHE Ⅱ\u003csup\u003ea\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e16.94\u0026thinsp;\u0026plusmn;\u0026thinsp;4.97\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e15.499\u0026thinsp;\u0026plusmn;\u0026thinsp;4.21\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e6.95\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSurgery\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e152(28.41)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e541(22.28)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e9.19\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHypertension\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e89(16.63)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e318(13.10)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e4.63\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.03\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eDiabetes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e53(9.91)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e192(7.91)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e2.31\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.13\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCHD\u003csup\u003eb\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e52(9.72)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e228(9.39)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.06\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.81\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCerebrovascular disease\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e112(20.93)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e311(12.81)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e23.65\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCOPD\u003csup\u003ec\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e29(5.42)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e197(8.11)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e4.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.03\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eImmunosuppression\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e9(1.68)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e35(1.44)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.17\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.68\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePneumonia\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e477(89.16)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e1872(77.10)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e38.80\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBloodstream infections\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e169(31.59)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e338(13.92)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e96.49\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eIntro-abdominal infections\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e87(16.26)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e403(16.60)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.04\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.85\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eUrinary infections\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e97(18.13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e153(6.30)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e779.41\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSkin infections\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e19(3.55)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e46(1.89)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e55.61\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCentral system infections\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e26(4.86)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e49(2.02)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e14.35\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePelvic infection\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2(0.37)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e11(0.45)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.06\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.80\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eKlebsiella pneumoniae\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e178(33.27)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e136(5.60)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e354.27\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAcinetobacter baumanii\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e214(40.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e41(1.69)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e818.09\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eStenotrophomonas maltophilia\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e22(4.11)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e221(9.10)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e32.32\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eEscherichia coli\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e62(11.59)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e70(2.88)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e78.06\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePseudomonas aeruginosa\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e102(19.07)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e72(2.97)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e205.58\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eStaphylococcus aureus\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e33(6.17)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e49(22.01)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e9.62\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eStaphylococcus epidermidis\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e19(3.55)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e14(0.58)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e35.23\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eEnterococcus faecium\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e30(3.6)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e9(0.37)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e105.45\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCandida albicans\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e330(5.61)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e89(3.67)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e4.29\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.04\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAspergillus\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e6(1.12)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e27(1.11)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.00\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.99\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"5\"\u003e\u003csup\u003ea\u003c/sup\u003eAPACHE: Acute Physiology and Chronic Health Evaluation, \u003csup\u003eb\u003c/sup\u003eCHD: Coronary atherosclerotic heart disease, \u003csup\u003ec\u003c/sup\u003eCOPD: Chronic obstructive pulmonary disease. * Comparison between two groups, *group and*group. The difference between groups was statistically significant (P\u0026thinsp;\u0026lt;\u0026thinsp;0.01 or P\u0026thinsp;\u0026lt;\u0026thinsp;0.05).\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec13\" class=\"Section2\"\u003e\u003ch2\u003eInfection characteristic, risk factors and prediction model of multidrug resistance\u003c/h2\u003e\u003cp\u003eAmong the infection episodes, the incidence of multidrug resistance was 27.84%, and the incidence of multidrug resistance was 18.06%. There were 23 indictors including age(\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), female(\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), region(\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), hospital grades(\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), surgery(\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), APACHE Ⅱ(\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), hypertension(\u003cem\u003ep\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.03), Cerebrovascular disease(\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), COPD(\u003cem\u003ep\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.03), pneumonia(\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), bloodstream infections(\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), urinary infections(\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), skin infection(\u003cem\u003ep\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.02), central system infections(\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), Klebsiella pneumoniae(\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), Acinetobacter baumanii(\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), Stenotrophomonas maltophilia(\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), Escherichia coli(\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), Pseudomonas aeruginosa(\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), Staphylococcus aureus(\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), Staphylococcus epidermidis(\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), Enterococcus faecium(\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), and Candida albicans(\u003cem\u003ep\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.04) by univariate analysis.\u003c/p\u003e\u003cp\u003eThe training set contained 2074 samples and the validation set comprised 889 samples for machine learning algorithms. In the validation set, AUC value of multidrug resistance was 0.86(0.83\u0026ndash;0.90) in LR, 0.86(0.82\u0026ndash;0.89) in RF, 0.85(0.81\u0026ndash;0.88) in XGBoost, and 0.85(0.82\u0026ndash;0.89) in GBM (Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e). There were no statistically significant differences in AUC between any of four prediction models (Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e). We selected the LR algorithms for the final model. A nomogram of multidrug resistance for ICU patients with suspected infections was created based on independent risk factors including APACHE Ⅱ (1.06, 95%CI 1.03\u0026ndash;1.1, \u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), bloodstream infections (1.82, 95%CI 1.26\u0026ndash;2.61, \u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), urinary infections (3.42, 95%CI 2.20\u0026ndash;5.30, \u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), Klebsiella pneumoniae (11.67, 95%CI 7.91\u0026ndash;17.21, \u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), Acinetobacter baumanii (85.22, 95%CI 50.03-145.18, \u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), and Enterococcus faecium (22.10, 95%CI 8.58\u0026ndash;56.93, \u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01)(Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e).\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab4\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eAnalysis of the differences in AUC values among different machine learning models of multidrug resistance\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"7\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eModels\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eAUC1\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eSE1\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eAUC2\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eSE2\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003ez\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLR\u003csup\u003e*\u003c/sup\u003e_predvalue VS RF\u003csup\u003e*\u003c/sup\u003e_predvalue\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.86\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.86\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e-0.10\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.92\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLR_predvalue VS GBM\u003csup\u003e*\u003c/sup\u003e_prevalue\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.86\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.85\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e1.05\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.29\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLR_predvalue VS XGB\u003csup\u003e*\u003c/sup\u003e _prevalue\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.86\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.86\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.32\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.75\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRF_predvalue VS GBM_prevalue\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.86\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.015\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.85\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e1.04\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.23\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRF_predvalue VS XGB_prevalue\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.86\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.86\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.43\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.67\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGBM_prevalue VS XGB _prevalue\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.85\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.86\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e-1.06\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.29\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"7\"\u003e*LR: logistic regression, RF: random forest, GMB: gradient boosting machine, XGB: extreme gradient boosting.\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e"},{"header":"Discussion","content":"\u003cp\u003eWe conducted a prospective study of infections in patients admitted to the ICU across 16 provinces in China. The results showed that pneumonia and bloodstream infections were the main infections caused by Gram-negative bacteria, especially Klebsiella pneumoniae. We explore the ability of four machine learning algorithms to predict the risk of mortality and multidrug resistance for ICU patients with suspected infections. The final prediction model achieved an AUC value of 0.87 (0.84\u0026ndash;0.91) for mortality and 0.86(0.83\u0026ndash;0.90) for multidrug resistance based on the logistic regression. Independent risk factors of mortality (surgery, APACHE Ⅱ, and bloodstream infections) and multidrug resistance (APACHE Ⅱ, bloodstream infections, urinary infections, Klebsiella pneumoniae, Acinetobacter baumanii, and Enterococcus faecium) were identified by the logistic regression model.\u003c/p\u003e\u003cp\u003eIn this study, surgery, APACHE Ⅱ, and bloodstream infections were independent risk factors for mortality of patients with suspected infection when they admitted to ICU. Bloodstream infections with a 30-day mortality rate of 15%, usually develop into severe sepsis, septic shock and multiple organ dysfunction, requiring admission to the ICU[\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e]. Previous studies demonstrate that gram-negative bacteria are the most common isolates form bloodstream infections which increased incidence, especially among elderly patients[\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e]. Enterococcus species following urinary tract infections, intraabdominal infections, device infections, and endocarditis represent the third leading cause of nosocomial bloodstream infections in the US[\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e]. A study focusing on the mortality of critically ill surgical patients found that abdominal infections emerged as the most prevalent site of infection but genitourinary infections correlated with the highest mean lactate and the highest proportion of patients experiencing septic shock[\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eWe found that APACHE Ⅱ, bloodstream infections, urinary infections, Klebsiella pneumoniae, Acinetobacter baumanii, and Enterococcus faecium were independent risk factors of multidrug resistance for patients with suspected infections when they admitted to ICU. According to the US Centers for Disease Control and Prevention, more than 70% of patients receive antibiotics during their stay in the ICU[\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. Timely and adequate using of antibiotic therapy are an important determinant of survival in critically ill patients in the ICU. Inappropriate antibiotic use leads to infections of multidrug-resistant bacteria that prolong the length of stay and duration of mechanical ventilation[\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e]. The prognosis of patients who develop multidrug-resistant infections is poor, which increases the economic burden and mortality rates[\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e, \u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e]. Klebsiella pneumoniae is the second most common cause of Gram-negative bacteraemia even as an opportunistic pathogen[\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e]. Klebsiella pneumoniae causes resistance to many antimicrobials because of their plasmids encoding extended-spectrum beta-lactamases and the acquisition of carbapenemases[\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eIn recent years, artificial intelligence applications have predominantly centered on machine learning methodologies. Contemporary techniques such as neural networks, support vector machines, and random forests have been increasingly utilized to develop predictive models and identify risk factors[\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e, \u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e]. However, conventional statistical approaches face inherent limitations when processing large volumes of unrefined variables. In our study, logistic regression (LR) was not slightly worse than the other three prediction models. This advantage likely stems from the constrained nature of the characteristics of patients with suspected infection assessment metric. We anticipate machine learning algorithms will emerge as powerful tools for predicting complex clinical outcomes, holding significant promise for future applications.\u003c/p\u003e\u003cp\u003eThis study also has certain limitations. Firstly, the sample may not be representative of all patients with infection admitted to ICUs in China. Secondly, we did not select overall patient characteristics during the same ICU admission period. We did not know the rate of infection because the data was not complete for all patients. Finally, we validated our models by the same dataset. For example, internal validation cannot detect systematic biases in sampling frameworks. Models may exhibit excellent cross-validation metrics yet fail when applied to populations with divergent feature distributions. However, this is the first study to identify independent risk factors for the mortality and multidrug resistance of patients with suspected infection when they admitted to ICU using a machine learning algorithm and the findings of this study may form the basis for a further investigation in the future.\u003c/p\u003e"},{"header":"Conclusion","content":"\u003cp\u003eIn conclusion, pneumonia was the main reason why patients with infection were admitted to the ICU. By means of machine learning techniques, surgery, APACHE Ⅱ, and bloodstream infections were the independent risk factors of the mortality, while APACHE Ⅱ, bloodstream infections, urinary infections, and infected with Klebsiella pneumoniae or Acinetobacter baumanii or Enterococcus faecium were the independent risk factors of multidrug resistance of patients with suspected infection when they admitted to ICU.\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003cdiv class=\"DefinitionList\"\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eICU\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eintensive care unit\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eAPACHE\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eAcute Physiology and Chronic Health Evaluation\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eCHD\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eCoronary atherosclerotic heart disease\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eCOPD\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eChronic obstructive pulmonary disease\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eICU LOS\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eIntensive care unit length of stay\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eDRI\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eDrug Resistant Infection\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eMDR\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eMultidrug Resistant Infection\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eEDC\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eElectronic data capture. LR:logistic regression\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eRF\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003erandom forest\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eXGBoost\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eextreme gradient boosting\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eGBM\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003egradient boosting machine\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eROC\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eReceiver Operating Characteristic\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eAUC\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003earea under the curve of receiver operating characteristic.\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003c/div\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eClinical trial registration\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eTh trial protocol was registered at ClinicalTrials.gov (Identifier: NCT 04966390, Registration Date: July 14, 2021). The full record can be accessed at: https://clinicaltrials.gov/show/NCT04966390\u003c/p\u003e\u003cp\u003e\u003ch2\u003eEthics approval and consent to participate\u003c/h2\u003e\u003cp\u003e This study was approved by medical ethics committee of Peking University People\u0026rsquo;s Hospital (2021PHB020-001, Beijing, China). Written informed consent was obtained from all participants prior to the enrollment of this study.\u003c/p\u003e\u003c/p\u003e\u003cp\u003e\u003ch2\u003eConsent publication\u003c/h2\u003e\u003cp\u003eNot applicable.\u003c/p\u003e\u003c/p\u003e\u003cp\u003e\u003ch2\u003eCompeting interests\u003c/h2\u003e\u003cp\u003eThe authors declared no potential conflict of interest concerning the research, authorship, and/or publication of this article.\u003c/p\u003e\u003c/p\u003e\u003ch2\u003eFunding\u003c/h2\u003e\u003cp\u003eThis study was funded by the National Natural Science Foundation of China (grant number 82202366).\u003c/p\u003e\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\u003cp\u003eSY and HZ designed the study. SY and TW participated in the literature search, analysis of data, as well as manuscript writing. YS and WS participated in the literature search and data analysis and YA revised the manuscript. HZ participated in the data analysis and revised the manuscript. HZ had made contributions to the acquisition, analysis of data. HZ and YA are corresponding authors and are responsible for ensuring that all listed authors have approved the manuscript before submission.\u003c/p\u003e\u003ch2\u003eAcknowledgement\u003c/h2\u003e\u003cp\u003eThank you for all patients for their participation in this study and all participants for accomplishing this study. We thank Hua Rong for her electronic information technology. For continuous support, assistance, and cooperation, we thank Chen Li(QiLu Hospital of Shandong University), Li Kong(Affiliated Hospital of Shandong University of Traditional Chinese Medicine), Tingfa Zhou(Lin Yi People\u0026rsquo;Hospital), Haiming Jiang(The Second of Clinical Medicine of Binzhou Medical university), Xugang Li(Ri Zhao LinYi People\u0026rsquo;Hospital), Yun Jin(Zi Bo First Hospital), Qiang Sun(Affiliated Hospital of Jining Medical University), Long Qin(Tsinghua University Yuquan Hospital), Qin Dong(The First Affiliated Hospital of Xi\u0026rsquo;An Jiao Tong University), Xiaochuang Wang(The Second Affiliated Hospital of Xi\u0026rsquo;An Jiao Tong University), Yong Li(Bao Ji People\u0026rsquo;s Hospital), Chuan Guo(School of Clinical Medicine\u0026amp; The First Affiliated Hospital of Chengdu Medical College), Xiaobo Huang, Xiaoqin Zhang(Sichuan Academy of Medical Sciences Sichuan Provincial People\u0026rsquo;s Hospital), Chuan Zhang(Cheng Du third People\u0026rsquo;s Hospital), Hongde Chen(Cheng Du Tenth People\u0026rsquo;s Hospital), Yu Du(Sichuan University Fourth Hospital), Hang Xu(The First Affiliated Hospital of ShiHeZi University), Xianying Lei(Affiliated Hospital of Southwest Medical University), Junjing Luo(The First Affiliated Hospital of Xinxiang medical university), Weidong Guo(Xin Xiang Central Hospital), Yinjiang Change(Pu Yang People\u0026rsquo;s Hospital), Yiyi Sun(He Bi People\u0026rsquo;s Hospital), Hua Li(The Second Affiliated Hospital of Henan Chinese Medical University), Zhengrong Mao(The First Affiliated Hospital of Henan Chinese Medical University), Li Chen(Affiliated Hospital of North Sichuan Medical College), Faming He(Chest Hospital of Zhengzhou University),Chaogui Zhang(Yi Bin Second People\u0026rsquo;s Hospital), Yonghui Fan(General Hospital of Pingmei Shenma Group), Jianghua Zhu(The First Affiliated Hospital of Ningbo Hospital),Peili Chen(Shang Qiu First People\u0026rsquo;s Hospital), Yong Cui(Chongqing University Three Gorges Hospital), Guolong Cai(Zhe Jiang Hospital), Ken Chen(Karamay Central Hospital of Xinjiang), Jian Chen(Affiliated Hospital of Xinjiang Chinese Medical University), Xiangcheng Zhang(Huai An First People\u0026rsquo;s Hospital), Tianzeng Zhang(An Yang District Hospital), Yuling Liu(Jiaozuo Coal Industry [Group] Co., Ltd. Central Hospital), Chao Jia(Mian Yang Central Hospital), Lifang Wu(Da Feng People\u0026rsquo;s Hospital), Jiangquan Yu(Northern Jiangsu People\u0026rsquo;s Hospital), Fang Huang(The First Affiliated Hospital of Soochow University), Yishan Zheng(Nan Jing Sencod Hospital), Xingui Dai(The First Affiliated Hospital of Xiangnan University), Jiangliang Zhou(Huai Hua First People\u0026rsquo;s Hospital), Xinju Xu(Jiao Zuo Second People\u0026rsquo;s Hospital), Mingfan Yang(Huo Qiu First People\u0026rsquo;s Hospital), Liujiu Tian(An Qing First People\u0026rsquo;s Hospital), Chunli Yang(The First Affiliated Hospital of Nanchang University), Guohui Yang, Jiangquan Fu(Affiliated Hospital of Guizhou Medical University), Donghao Wang(Tianjin Medical University Cancer Institute \u0026amp; Hospital), Youjie Qiao, Jing Wang(Tian Jing People\u0026rsquo;s Hospital), Bin Chen(The Second Affiliated Hospital of Tianjin Medical University), Baohua Wang, Aiguo Zhang, Yinhua Wang(North China of Science and Technology University Affiliated Hospital), Huisheng Qi(Tangshan Municipal Worker\u0026rsquo;s Hospital), Hongmei Qin(Yu Lin First People\u0026rsquo;s Hospital), Baoshan Li(Yun Cheng Central Hospital), Liang Luo(Wu Xi Second People\u0026rsquo;s Hospital) Jian Luo, Chungen Nie(Ji An People\u0026rsquo;s Hospital), Shichang Deng, Yonghong Deng(Yu Du People\u0026rsquo;s Hospital).\u003c/p\u003e\u003ch2\u003eData Availability\u003c/h2\u003e\u003cp\u003eThe data are available from the corresponding author on reasonable request. But the datasets are not publicly available due to privacy or ethical restrictions.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eVincent JL, Rello J, Marshall J, Silva E, Anzueto A, Martin CD, Moreno R, Lipman J, Gomersall C, Sakr Y\u003cem\u003e et al\u003c/em\u003e: \u003cstrong\u003eInternational study of the prevalence and outcomes of infection in intensive care units\u003c/strong\u003e. \u003cem\u003eJama \u003c/em\u003e2009, \u003cstrong\u003e302\u003c/strong\u003e(21):2323-2329.\u003c/li\u003e\n\u003cli\u003eFinfer S, Bellomo R, Lipman J, French C, Dobb G, Myburgh J: \u003cstrong\u003eAdult-population incidence of severe sepsis in Australian and New Zealand intensive care units\u003c/strong\u003e. \u003cem\u003eIntensive care medicine \u003c/em\u003e2004, \u003cstrong\u003e30\u003c/strong\u003e(4):589-596.\u003c/li\u003e\n\u003cli\u003eHanberger H, Garcia-Rodriguez JA, Gobernado M, Goossens H, Nilsson LE, Struelens MJ: \u003cstrong\u003eAntibiotic susceptibility among aerobic gram-negative bacilli in intensive care units in 5 European countries. French and Portuguese ICU Study Groups\u003c/strong\u003e. \u003cem\u003eJama \u003c/em\u003e1999, \u003cstrong\u003e281\u003c/strong\u003e(1):67-71.\u003c/li\u003e\n\u003cli\u003eVincent JL, Bihari DJ, Suter PM, Bruining HA, White J, Nicolas-Chanoin MH, Wolff M, Spencer RC, Hemmer M: \u003cstrong\u003eThe prevalence of nosocomial infection in intensive care units in Europe. Results of the European Prevalence of Infection in Intensive Care (EPIC) Study. EPIC International Advisory Committee\u003c/strong\u003e. \u003cem\u003eJama \u003c/em\u003e1995, \u003cstrong\u003e274\u003c/strong\u003e(8):639-644.\u003c/li\u003e\n\u003cli\u003eVincent JL, Sakr Y, Sprung CL, Ranieri VM, Reinhart K, Gerlach H, Moreno R, Carlet J, Le Gall JR, Payen D: \u003cstrong\u003eSepsis in European intensive care units: results of the SOAP study\u003c/strong\u003e. \u003cem\u003eCrit Care Med \u003c/em\u003e2006, \u003cstrong\u003e34\u003c/strong\u003e(2):344-353.\u003c/li\u003e\n\u003cli\u003eBrusselaers N, Vogelaers D, Blot S: \u003cstrong\u003eThe rising problem of antimicrobial resistance in the intensive care unit\u003c/strong\u003e. \u003cem\u003eAnnals of intensive care \u003c/em\u003e2011, \u003cstrong\u003e1\u003c/strong\u003e:47.\u003c/li\u003e\n\u003cli\u003eGoldmann DA, Weinstein RA, Wenzel RP, Tablan OC, Duma RJ, Gaynes RP, Schlosser J, Martone WJ: \u003cstrong\u003eStrategies to Prevent and Control the Emergence and Spread of Antimicrobial-Resistant Microorganisms in Hospitals. A challenge to hospital leadership\u003c/strong\u003e. \u003cem\u003eJama \u003c/em\u003e1996, \u003cstrong\u003e275\u003c/strong\u003e(3):234-240.\u003c/li\u003e\n\u003cli\u003eLipsitch M, Bergstrom CT, Levin BR: \u003cstrong\u003eThe epidemiology of antibiotic resistance in hospitals: paradoxes and prescriptions\u003c/strong\u003e. \u003cem\u003eProc Natl Acad Sci U S A \u003c/em\u003e2000, \u003cstrong\u003e97\u003c/strong\u003e(4):1938-1943.\u003c/li\u003e\n\u003cli\u003eGupta R, Malik A, Rizvi M, Ahmed M, Singh A: \u003cstrong\u003eEpidemiology of multidrug-resistant Gram-negative pathogens isolated from ventilator-associated pneumonia in ICU patients\u003c/strong\u003e. \u003cem\u003eJournal of global antimicrobial resistance \u003c/em\u003e2017, \u003cstrong\u003e9\u003c/strong\u003e:47-50.\u003c/li\u003e\n\u003cli\u003eKalın G, Alp E, Chouaikhi A, Roger C: \u003cstrong\u003eAntimicrobial Multidrug Resistance: Clinical Implications for Infection Management in Critically Ill Patients\u003c/strong\u003e. \u003cem\u003eMicroorganisms \u003c/em\u003e2023, \u003cstrong\u003e11\u003c/strong\u003e(10).\u003c/li\u003e\n\u003cli\u003eSeymour CW, Liu VX, Iwashyna TJ, Brunkhorst FM, Rea TD, Scherag A, Rubenfeld G, Kahn JM, Shankar-Hari M, Singer M\u003cem\u003e et al\u003c/em\u003e: \u003cstrong\u003eAssessment of Clinical Criteria for Sepsis: For the Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3)\u003c/strong\u003e. \u003cem\u003eJama \u003c/em\u003e2016, \u003cstrong\u003e315\u003c/strong\u003e(8):762-774.\u003c/li\u003e\n\u003cli\u003eHumphries R, Bobenchik AM, Hindler JA, Schuetz AN: \u003cstrong\u003eOverview of Changes to the Clinical and Laboratory Standards Institute Performance Standards for Antimicrobial Susceptibility Testing, M100, 31st Edition\u003c/strong\u003e. \u003cem\u003eJ Clin Microbiol \u003c/em\u003e2021, \u003cstrong\u003e59\u003c/strong\u003e(12):e0021321.\u003c/li\u003e\n\u003cli\u003eKoo HJ, Lim S, Choe J, Choi SH, Sung H, Do KH: \u003cstrong\u003eRadiographic and CT Features of Viral Pneumonia\u003c/strong\u003e. \u003cem\u003eRadiographics : a review publication of the Radiological Society of North America, Inc \u003c/em\u003e2018, \u003cstrong\u003e38\u003c/strong\u003e(3):719-739.\u003c/li\u003e\n\u003cli\u003eAlmirall J, Serra-Prat M, Bol\u0026iacute;bar I, Balasso V: \u003cstrong\u003eRisk Factors for Community-Acquired Pneumonia in Adults: A Systematic Review of Observational Studies\u003c/strong\u003e. \u003cem\u003eRespiration; international review of thoracic diseases \u003c/em\u003e2017, \u003cstrong\u003e94\u003c/strong\u003e(3):299-311.\u003c/li\u003e\n\u003cli\u003eOttosen J, Evans H: \u003cstrong\u003ePneumonia: challenges in the definition, diagnosis, and management of disease\u003c/strong\u003e. \u003cem\u003eThe Surgical clinics of North America \u003c/em\u003e2014, \u003cstrong\u003e94\u003c/strong\u003e(6):1305-1317.\u003c/li\u003e\n\u003cli\u003eTimsit JF, Rupp\u0026eacute; E, Barbier F, Tabah A, Bassetti M: \u003cstrong\u003eBloodstream infections in critically ill patients: an expert statement\u003c/strong\u003e. \u003cem\u003eIntensive care medicine \u003c/em\u003e2020, \u003cstrong\u003e46\u003c/strong\u003e(2):266-284.\u003c/li\u003e\n\u003cli\u003eSartelli M, Chichom-Mefire A, Labricciosa FM, Hardcastle T, Abu-Zidan FM, Adesunkanmi AK, Ansaloni L, Bala M, Balogh ZJ, Beltr\u0026aacute;n MA\u003cem\u003e et al\u003c/em\u003e: \u003cstrong\u003eThe management of intra-abdominal infections from a global perspective: 2017 WSES guidelines for management of intra-abdominal infections\u003c/strong\u003e. \u003cem\u003eWorld journal of emergency surgery : WJES \u003c/em\u003e2017, \u003cstrong\u003e12\u003c/strong\u003e:29.\u003c/li\u003e\n\u003cli\u003eRowe TA, Juthani-Mehta M: \u003cstrong\u003eUrinary tract infection in older adults\u003c/strong\u003e. \u003cem\u003eAging health \u003c/em\u003e2013, \u003cstrong\u003e9\u003c/strong\u003e(5).\u003c/li\u003e\n\u003cli\u003eMoffarah AS, Al Mohajer M, Hurwitz BL, Armstrong DG: \u003cstrong\u003eSkin and Soft Tissue Infections\u003c/strong\u003e. \u003cem\u003eMicrobiol Spectr \u003c/em\u003e2016, \u003cstrong\u003e4\u003c/strong\u003e(4).\u003c/li\u003e\n\u003cli\u003eHe T, Kaplan S, Kamboj M, Tang YW: \u003cstrong\u003eLaboratory Diagnosis of Central Nervous System Infection\u003c/strong\u003e. \u003cem\u003eCurr Infect Dis Rep \u003c/em\u003e2016, \u003cstrong\u003e18\u003c/strong\u003e(11):35.\u003c/li\u003e\n\u003cli\u003eMitchell C, Prabhu M: \u003cstrong\u003ePelvic inflammatory disease: current concepts in pathogenesis, diagnosis and treatment\u003c/strong\u003e. \u003cem\u003eInfect Dis Clin North Am \u003c/em\u003e2013, \u003cstrong\u003e27\u003c/strong\u003e(4):793-809.\u003c/li\u003e\n\u003cli\u003eMagiorakos AP, Srinivasan A, Carey RB, Carmeli Y, Falagas ME, Giske CG, Harbarth S, Hindler JF, Kahlmeter G, Olsson-Liljequist B\u003cem\u003e et al\u003c/em\u003e: \u003cstrong\u003eMultidrug-resistant, extensively drug-resistant and pandrug-resistant bacteria: an international expert proposal for interim standard definitions for acquired resistance\u003c/strong\u003e. \u003cem\u003eClinical microbiology and infection : the official publication of the European Society of Clinical Microbiology and Infectious Diseases \u003c/em\u003e2012, \u003cstrong\u003e18\u003c/strong\u003e(3):268-281.\u003c/li\u003e\n\u003cli\u003eLaupland KB, Gregson DB, Zygun DA, Doig CJ, Mortis G, Church DL: \u003cstrong\u003eSevere bloodstream infections: a population-based assessment\u003c/strong\u003e. \u003cem\u003eCrit Care Med \u003c/em\u003e2004, \u003cstrong\u003e32\u003c/strong\u003e(4):992-997.\u003c/li\u003e\n\u003cli\u003eReunes S, Rombaut V, Vogelaers D, Brusselaers N, Lizy C, Cankurtaran M, Labeau S, Petrovic M, Blot S: \u003cstrong\u003eRisk factors and mortality for nosocomial bloodstream infections in elderly patients\u003c/strong\u003e. \u003cem\u003eEuropean journal of internal medicine \u003c/em\u003e2011, \u003cstrong\u003e22\u003c/strong\u003e(5):e39-44.\u003c/li\u003e\n\u003cli\u003eIke Y: \u003cstrong\u003e[Pathogenicity of Enterococci]\u003c/strong\u003e. \u003cem\u003eNihon saikingaku zasshi Japanese journal of bacteriology \u003c/em\u003e2017, \u003cstrong\u003e72\u003c/strong\u003e(2):189-211.\u003c/li\u003e\n\u003cli\u003eBin Ghaffar W, Nazir S, Siddiqui S, Abdul Ghaffar MB, Khan MF, Latif A, Cheema Z, Hanif S, Sohaib M: \u003cstrong\u003eAssociation Between the Site of Infection and Mortality Analysis in Critically Ill Surgical Patients\u003c/strong\u003e. \u003cem\u003eCureus \u003c/em\u003e2023, \u003cstrong\u003e15\u003c/strong\u003e(12):e50033.\u003c/li\u003e\n\u003cli\u003eReacher MH, Shah A, Livermore DM, Wale MC, Graham C, Johnson AP, Heine H, Monnickendam MA, Barker KF, James D\u003cem\u003e et al\u003c/em\u003e: \u003cstrong\u003eBacteraemia and antibiotic resistance of its pathogens reported in England and Wales between 1990 and 1998: trend analysis\u003c/strong\u003e. \u003cem\u003eBMJ (Clinical research ed) \u003c/em\u003e2000, \u003cstrong\u003e320\u003c/strong\u003e(7229):213-216.\u003c/li\u003e\n\u003cli\u003eSiegel JD, Rhinehart E, Jackson M, Chiarello L: \u003cstrong\u003eManagement of multidrug-resistant organisms in health care settings, 2006\u003c/strong\u003e. \u003cem\u003eAmerican journal of infection control \u003c/em\u003e2007, \u003cstrong\u003e35\u003c/strong\u003e(10 Suppl 2):S165-193.\u003c/li\u003e\n\u003cli\u003eNeidell MJ, Cohen B, Furuya Y, Hill J, Jeon CY, Glied S, Larson EL: \u003cstrong\u003eCosts of healthcare- and community-associated infections with antimicrobial-resistant versus antimicrobial-susceptible organisms\u003c/strong\u003e. \u003cem\u003eClinical infectious diseases : an official publication of the Infectious Diseases Society of America \u003c/em\u003e2012, \u003cstrong\u003e55\u003c/strong\u003e(6):807-815.\u003c/li\u003e\n\u003cli\u003eCubero M, Grau I, Tubau F, Pallar\u0026eacute;s R, Dom\u0026iacute;nguez M, Li\u0026ntilde;ares J, Ardanuy C: \u003cstrong\u003eMolecular Epidemiology of Klebsiella pneumoniae Strains Causing Bloodstream Infections in Adults\u003c/strong\u003e. \u003cem\u003eMicrobial drug resistance (Larchmont, NY) \u003c/em\u003e2018, \u003cstrong\u003e24\u003c/strong\u003e(7):949-957.\u003c/li\u003e\n\u003cli\u003eParamythiotou E, Routsi C: \u003cstrong\u003eAssociation between infections caused by multidrug-resistant gram-negative bacteria and mortality in critically ill patients\u003c/strong\u003e. \u003cem\u003eWorld journal of critical care medicine \u003c/em\u003e2016, \u003cstrong\u003e5\u003c/strong\u003e(2):111-120.\u003c/li\u003e\n\u003cli\u003eDesai RJ, Wang SV, Vaduganathan M, Evers T, Schneeweiss S: \u003cstrong\u003eComparison of Machine Learning Methods With Traditional Models for Use of Administrative Claims With Electronic Medical Records to Predict Heart Failure Outcomes\u003c/strong\u003e. \u003cem\u003eJAMA network open \u003c/em\u003e2020, \u003cstrong\u003e3\u003c/strong\u003e(1):e1918962.\u003c/li\u003e\n\u003cli\u003eMortazavi BJ, Bucholz EM, Desai NR, Huang C, Curtis JP, Masoudi FA, Shaw RE, Negahban SN, Krumholz HM: \u003cstrong\u003eComparison of Machine Learning Methods With National Cardiovascular Data Registry Models for Prediction of Risk of Bleeding After Percutaneous Coronary Intervention\u003c/strong\u003e. \u003cem\u003eJAMA network open \u003c/em\u003e2019, \u003cstrong\u003e2\u003c/strong\u003e(7):e196835.\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"bmc-infectious-diseases","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"infd","sideBox":"Learn more about [BMC Infectious Diseases](http://bmcinfectdis.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/infd","title":"BMC Infectious Diseases","twitterHandle":"#bmcinfectdis","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Suspected infection, Mortality, Multidrug resistance","lastPublishedDoi":"10.21203/rs.3.rs-7333649/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7333649/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e\u003cp\u003eSuspected infection or infection may develop into sepsis or septic shock, leading to high mortality rate of patients admitted to ICU. However, suspected infection has not been fully characterized. We performed prediction models to identify independent risk factors of mortality and multidrug resistance for patients with suspected infection when they admitted to the ICU in mainland China.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e\u003cp\u003eA prospective analysis of Demographic, physiological and microbiological data were recorded for patients with suspected infection when they admitted to ICU between July 2021 and December 2022 in mainland China. Machine learning algorithms were employed to identify risk factors and create prediction models for mortality and multidrug resistance for patients with suspected infection. AUC were calculated and compared by bootstrap to evaluate prediction models.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e\u003cp\u003eA total of 2963 patients from 67 hospitals in mainland China were enrolled into this study. The most common sites of infection were the lung (79.28%), bloodstream (17.11%) and abdomen (16.54%). The mortality rate was 10.90%. Logistic regression prediction model with AUC value 0.87 was selected and identified surgery (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), APACHE Ⅱ (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), and bloodstream infection (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01) were independent risk factors of mortality. Furthermore, logistic regression prediction model exhibited the highest AUC (0.86) for predicting the risk of multidrug-resistant infections and identifying six independent risk factors including APACHE Ⅱ (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), bloodstream infections (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), urinary infections (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), Klebsiella pneumoniae (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), Acinetobacter baumanii (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01), and Enterococcus faecium (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01).\u003c/p\u003e\u003ch2\u003eConclusions\u003c/h2\u003e\u003cp\u003eThe most common infection was pneumonia for patients admitted to ICU in mainland China. By means of machine learning techniques, we selected independent risk factors, as well as evaluated prediction models for the mortality and multidrug resistance of patients with suspected infection when they admitted to ICU.\u003c/p\u003e","manuscriptTitle":"Machine Learning-Based Prediction of Mortality and Multidrug-Resistant Infection Risks in ICU Patients with Suspected Infection: A Prospective National Multicenter Cohort StudyAuthor information","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-17 11:05:57","doi":"10.21203/rs.3.rs-7333649/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-10-06T12:49:55+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-04T12:42:19+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-04T04:47:33+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"253436780252732792628644888087799620360","date":"2025-09-25T13:59:42+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"243751629950254631928339282165061980373","date":"2025-09-25T02:06:48+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-24T23:24:57+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"4443568448184600727653901943890383203","date":"2025-09-24T23:11:24+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"314612079464296120465049190309741455101","date":"2025-09-22T18:46:27+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-22T15:32:24+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"12857544018412180603443955652331698247","date":"2025-09-12T13:10:00+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-09T19:18:11+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-08-20T19:06:41+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-08-18T03:24:09+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-08-18T03:22:43+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Infectious Diseases","date":"2025-08-09T11:33:48+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-infectious-diseases","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"infd","sideBox":"Learn more about [BMC Infectious Diseases](http://bmcinfectdis.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/infd","title":"BMC Infectious Diseases","twitterHandle":"#bmcinfectdis","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"d9fcb5af-7db9-4a97-818a-c0115aa93328","owner":[],"postedDate":"September 17th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-12-22T16:00:12+00:00","versionOfRecord":{"articleIdentity":"rs-7333649","link":"https://doi.org/10.1186/s12879-025-12354-8","journal":{"identity":"bmc-infectious-diseases","isVorOnly":false,"title":"BMC Infectious Diseases"},"publishedOn":"2025-12-20 15:57:07","publishedOnDateReadable":"December 20th, 2025"},"versionCreatedAt":"2025-09-17 11:05:57","video":"","vorDoi":"10.1186/s12879-025-12354-8","vorDoiUrl":"https://doi.org/10.1186/s12879-025-12354-8","workflowStages":[]},"version":"v1","identity":"rs-7333649","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7333649","identity":"rs-7333649","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}