Development and validation of machine learning-based models for predicting healthcare-associated bacterial/fungal infections among COVID-19 inpatients: a retrospective cohort study

Development and validation of machine learning-based models for predicting healthcare-associated bacterial/fungal infections among COVID-19 inpatients: a retrospective cohort study | 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 Development and validation of machine learning-based models for predicting healthcare-associated bacterial/fungal infections among COVID-19 inpatients: a retrospective cohort study Min Wang, Wenjuan Li, Hui Wang, Peixin song This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3847614/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 14 Apr, 2024 Read the published version in Antimicrobial Resistance & Infection Control → Version 1 posted 8 You are reading this latest preprint version Abstract Background COVID-19 and bacterial/fungal coinfections have posed significant challenges to human health. However, there is a lack of good tools for predicting coinfection risk to aid clinical work. Objective We aimed to investigate the risk factors for bacterial/fungal coinfection among COVID-19 patients and to develop machine learning models to estimate the risk of coinfection. Methods In this retrospective cohort study, we enrolled adult inpatients confirmed with COVID-19 in a tertiary hospital between January 1 and July 31, 2023, in China and collected baseline information at admission. All the data were randomly divided into a training set and a testing set at a ratio of 7:3. We developed the generalized linear and random forest models for coinfections in the training set and assessed the performance of the models in the testing set. Decision curve analysis was performed to evaluate the clinical applicability. Results A total of 1244 patients were included in the training cohort with 62 healthcare-associated bacterial/fungal infections, while 534 were included in the testing cohort with 22 infections. We found that patients with comorbidities (diabetes, neurological disease) were at greater risk for coinfections than were those without comorbidities (OR = 2.79, 95%CI = 1.61–4.86; OR = 1.93, 95%CI = 1.11–3.35). An indwelling central venous catheter or urinary catheter was also associated with an increased risk (OR = 2.53, 95%CI = 1.39–4.64; OR = 2.28, 95%CI = 1.24–4.27) of coinfections. Patients with PCT > 0.5 ng/ml were 2.03 times (95%CI = 1.41–3.82) more likely to be infected. Interestingly, the risk of coinfection was also greater in patients with an IL-6 concentration < 10 pg/ml (OR = 1.69, 95%CI = 0.97–2.94). A creatinine concentration < 44 umol/L (OR = 0.40, 95%CI = 0.22–0.71) was a protective factor. The generalized linear and random forest models demonstrated favorable receiver operating characteristic curves (ROC = 0.87, 95%CI = 0.80–0.94; ROC = 0.88, 95%CI = 0.82–0.93) with high accuracy, sensitivity and specificity of 0.86vs0.75, 0.82vs0.86, 0.87vs0.74, respectively. The corresponding calibration evaluation P statistics were 0.883 and 0.769. Conclusions Our machine learning models achieved strong predictive ability and may be effective clinical decision support tools for identifying COVID-19 patients at risk for bacterial/fungal coinfection and guiding antibiotic administration. The levels of cytokines, such as IL-6, may affect the status of bacterial/fungal coinfection. machine learning predictive model bacterial/fungal infection healthcare-associated nosocomial infection Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Background Respiratory virus infections are associated with an increased risk of bacterial/fungal infections, especially in lower respiratory tract infections( 1 , 2 ). Current studies have reported that the prevalence of healthcare-associated bacterial/fungal infections in patients with COVID-19 ranges from 3.6–32%( 2 – 6 ). Researchers( 4 , 6 – 8 )have shown that COVID-19 and bacterial/fungal coinfections in those patients might contribute to worse outcomes, such as prolonged hospitalization and a higher mortality rate. The long-term impacts of viral and bacterial/fungal coinfections on antimicrobial resistance are severe public problems( 9 ). It is difficult for clinicians to identify coinfections early because of similar symptoms and signs, thus leading to a high rate of inappropriate prescription( 10 – 12 ). Early empiric antibiotic use varied from 27–84% across different hospitals( 10 ). Two multicenter cohort studies( 10 , 11 ) showed that the proportions of bacterial coinfection were lower than 10%, while the proportions of early empirical antibiotics were as high as 60%. However, without bacterial coinfections, antibiotic overuse not only does not benefit patients but also accelerates the development of antimicrobial resistance. Previous studies( 5 , 8 , 12 – 14 ) have focused on the characteristics and risk factors for bacterial coinfection in patients with COVID-19. In the literature, several predictors, such as PCT, CRP, steroid use, invasive ventilation, central venous catheter, urinary catheter, tocilizumab, length of stay, ICU admission, comorbidity, played significant roles in discriminating healthcare-associated bacterial coinfections( 1 , 2 , 4 , 5 , 12 , 14 – 16 ). Recent studies( 9 , 11 , 17 ) have used scientific statistical methods to estimate the risk of healthcare-associated bacterial coinfections in COVID-19 patients, instead of limiting the identification of risk factors. Estimating the probability of an individual developing healthcare-associated infections could help guide intervention earlier through patient care, microbiological testing and therapeutic measures. Therefore, establishing good predictive models has practical significance for clinical work and is beneficial for identifying high-risk patients and preventing and controlling them precisely. As machine learning (ML) is used for disease diagnosis or prognosis prediction, it is feasible to identify patients at high risk of bacterial coinfections( 18 ). Compared to traditional models, machine learning models have faster processors and smarter algorithms. Rapid progress in machine learning has provided opportunities for improved patient healthcare( 18 ). In this retrospective cohort study, we investigated the risk factors and established different ML models to predict the risk of healthcare-associated bacterial/fungal coinfections among inpatients with COVID-19. Method Inclusion and exclusion criteria Inpatients who tested positive for COVID-19 according to nasopharyngeal swab PCR between January 1 and July 31, 2023 in a tertiary hospital in China were included. This hospital serves a population of more than nine million people and provides tertiary referral services to the surrounding regions. The exclusion criteria were as follows: ( 1 ) patients under 18 years of age, ( 2 ) had a hospital stay less than three days, and ( 3 ) repeated patients. Study design and data collection In this retrospective, single-center cohort study, data including demographic information (age, sex, height, weight), comorbidity information (diabetes, hypertension, neurological diseases), and clinical records (operation history, invasive ventilation, urinary catheter), and laboratory results at admission (blood cell count, PCT, IL-6, creatinine) were collected directly from an electronic health record database. Clinicians and prevention and control professionals (IPCs) diagnosed and reported healthcare-associated bacterial/fungal coinfections under a healthcare-associated infection surveillance system and they reviewed the medical records of all patients with positive microbiological results to assess clinical significance (infection,colonization, or contamination). Data processing and Statistical analysis All the data processing and analysis were conducted using R (version 4.3.0). Missing value were processed for weight (n = 477,26.83%), height (n = 387,27.77%), white blood cell count (n = 6,0.34%), PCT(n = 481,27.05%), IL-6(n = 561,31.5%), neutrophil percent(n = 6,0.34%), lymphocyte count (n = 9,0.51%), CRP(n = 66,3.71%), creatinine(n = 82,4.61%), hemoglobin(n = 9,0.51%), albumin (n = 40,2.25%), glucose (n = 6,0.34%) according to multiple imputation method and were conducted for five imputations. Continuous variables are reported as the medians and inter-quartile ranges (IQRs) and were compared using the Kruskal-Wallis test. Categorical variables are reported as counts and percentages and were compared using the Chi-sq or Fisher’s exact test. We conducted univariate and stepwise multivariate logistic regression analyses to investigate risk factors for HA bacterial/fungal infection. Factors with a P-value less than 0.05 were independently associated with HA infections. Adjusted odds ratios (AORs) and 95% confidence intervals (95%CIs) were estimated. Model development and internal validation We randomly divided all the samples into a training set and a testing set at a ratio of 7:3. The training set was used to screen variables and develop models, while the testing set was used for model evaluation. We selected variables for the model development which were statistically significant in our univariate analysis. The models included 14 candidate predictors, as follows: diabetes, kidney disease, neurological disease, ICU admission, PCT_level, albumin (ALB_level), creatinine (Cr_level), IL-6_level, CRP_level, neutrophil (Ne_level), central venous catheter (CVC), urinary catheter (UC), invasive ventilation (IV), and dexamethasone (DXM). The variance inflation factors (VIF) were calculated to assess the multicollinearity of the predictors. As all the predictors had a VIF less than 2, indicating no multicollinearity, all the predictors were included in the model development. A random forest model was established (ntree = 500, mtry = 4) and the importance of the variables was determined. Our study compared the discrimination of models by the area under the receiver operating curve (AUCROC). The calibration slopes were calculated to check the risk of overfitting. Decision curve analyses were performed to evaluate whether the risk models improved clinical decision-making( 19 ). Results 1. Baseline characteristics A total of 1946 inpatients were diagnosed with laboratory-confirmed with COVID-19 between January 1 and July 31, 2023. As shown in the Fig. 1 , 1778 eligible inpatients were enrolled in this study. The median age of the patients was 69 years (interquartile rage (IQR), 56–80 years), and 1043 were male (58.66%). The Table 1 shows the difference in baseline characteristics between the HA infection group and the Non-HA infection group. Eighty-four (4.72%) patients developed healthcare-associated bacterial/fungal infections, 75 of whom were bacterial infections and 9 of whom had fungal infections. The most common bacterial strain isolated was klebsiella pneumoniae which was found in 18 patients and the main infection site was the lower respiratory tract. Table 1 Demographic characteristics, comorbidities, and laboratory test results for patients with HA bacterial/fungal infections and non-HA infections at baseline. Characteristics Total (N = 1778) HA infection (N = 84) Non-HA infection (N = 1694) c 2/W P Gender [n,%] 0.08 0.78 male 1043(58.66) 51(60.71) 992(58.56) female 735(41.34) 33(39.29) 702(43.44) Age, year [M,IQR] 69(56,80) 75(60,86.25) 68(56,79) 54978 < 0.001 BMI [M,IQR] 23.39(21.20,25.95) 22.59(19.82,24.34) 23.43(21.25,26.03) 27744 0.04 Hypertension [n,%] 1.34 0.25 Yes 896(50.39) 48(57.14) 848(50.06) No 882(46.61) 36(42.86) 846(49.94) Diabetes [n,%] 33.93 < 0.001 Yes 470(26.43) 47(55.95) 423(24.97) No 1308(73.56) 37(44.05) 1271(75.03) Tumor [n,%] 0.59 0.44 Yes 455(25.59) 25(29.76) 430(25.38) No 1323(74.41) 59(70.24) 1264(74.62) Kidney disease [n,%] 8.47 0.004 Yes 655(36.84) 44(52.38) 611(36.07) No 1123(63.16) 40(47.62) 1083(63.93) Neurological disease [n,%] 24.14 < 0.001 Yes 571(32.11) 48(57.14) 523(30.87) No 1207(67.89) 36(42.86) 1171(69.13) Operation[n,%] 0.09 0.76 Yes 351(19.74) 15(17.86) 336(19.83) No 1427(80.26) 69(82.14) 1358(80.17) ICU admission [n,%]: 11.24 < 0.001 Yes 111(6.24) 13(15.48) 98(5.79) No 1667(93.76) 71(84.52) 1596(94.21) Treatments before coinfections Invasive ventilation (IV)[n,%] 49.65 < 0.001 Yes 224(12.60) 32(38.10) 192(11.33) No 1554(87.40) 52(61.90) 1502(88.67) Urinary catheter (UC)[n,%] 58.08 < 0.001 Yes 566(31.83) 59(70.24) 507(29.93) No 1212(68.17) 25(29.76) 1187(70.07) Central venous catheter(CVC)[n,%] 53.34 < 0.001 Yes 433(24.35) 49(58.33) 384(22.67) No 1345(75.65) 35(41.67) 1310(77.33) Dexamethasone (DXM)[n,%] 21.69 < 0.001 Yes 537(30.20) 45(53.57) 492(29.04) No 1241(69.80) 39(46.43) 1202(70.96) Meprednisone(MEP) [n,%] 2.33 0.13 Yes 594(33.41) 35(41.67) 559(33.00) No 1184(66.59) 49(58.33) 1135(67.00) Tocilizumab ** (TZ)[n,%] 1 Yes 21(1.18) 1(1.19) 20(1.18) No 1757(98.82) 83(98.81) 1674(98.81) Laboratory test results on admission White blood cell count(WBC) * , 10 9 /L[M,IQR] 7.56(4.7,8.5) 7.15(5.5,10.20) 6.1(4.7,8.4) 56462 0.002 Neutrophil percent(Ne) * ,% [M,IQR] 70.21(59.80,82.20) 79.7(67.6,90.5) 70.6(59.5,81.6) 47654 3.818e-07 PCT * , ng/ml[M,IQR] 1.395(0.036,0.204) 0.14(0.068,1.503) 0.071(0.036,0.196) 34373 2.533e-06 IL-6 * ,pg/ml[M,IQR] 22.52(7.49,54.31) 18.02(5.538,42.815) 22.67(7.69,56.10) 33935 0.14 CRP * , mg/L[M,IQR] 12.10(3.9,34.53) 10.9(3.9,45.7) 50.3(10.5,114.15) 44715 1.889e-07 Albumin * (ALB), g/L [M,IQR] 35.7(32.42,39.20) 33(29.1,35.875) 36.3(32.6,39.3) 94897 1.452e-08 Lymphocyte count(Lym) * , [M,IQR] 2.198(0.7,1.6) 0.9(0.575,1.325) 1.1(0.7,1.6) 83667 0.005 Creatinine(Cr) * , umol/L[M,IQR] 34.41(4,47.88) 50.60(12.55,114.15) 10.9(3.9,45.2) 42972 3.622e-08 Hemoglobin(Hb) * , g/L [M,IQR] 117.1(104,133) 112.5(95.75,126.50) 120(104,133) 80214 0.04 Glucose(Glu) * , mmol/L [M,IQR] 6.584(4.52,7.29) 6.705(5.01,10.69) 5.26(4.5,7.14) 48508 5.007e-06 Length of hospital stay * , day [M,IQR] 13.12(7,16) 13(6,19) 11(7,16) 68409 0.55 The bold values indicate that these factors were statistically significant. M: median, IQR: interquartile range. * The statistical analysis were performed with the Kruskal-Wallis test. ** P-value calculated by Fisher’s exact probability method. According to random sampling results, a total of 1244 patients in the training set had 62 HA infections, while 534 patients in the testing set had 22 HA infections. There was no significant difference in the HA infection rate between the two groups ( P = 0.51). Table 2 Sampling results for the training set and testing set. Datasets HA infection Non-HA infection Total c 2 P The training set 62(4.98%) 1182(95.02%) 1244(69.97%) 0.44 0.51 The testing set 22(4.12%) 512(95.88%) 534(30.03%) Total 84(4.72%) 1694(95.28%) 1778(100.00%) 2. Model development 2.1 General linear model The result of the ANOVA test ( P = 0.66) indicated no significant difference between the full and stepwise models, and the AIC of the stepwise model was lower (417.22) than that of the full model (426.17). Thus, the stepwise logistic regression model was chosen as the final general linear model and included 7 predictors, as shown in Table 3 . 2.2 Independent risk factors According to the univariate analysis, 14 variables were associated with healthcare-associated bacterial/fungal infection, including diabetes, kidney disease (SZB), neurological disease (SJB), invasive ventilation (IV), urinary catheter (UC), central venous catheter (CVC), ICU admission, IL-6_level < 10 pg/ml, CRP_level 0.5 ng/ml, Cr_level < 44 umol/L, Ne_level < 80%, Lym_level < 0.2×10 9 /L, and dexamethasone (DXM) (P < 0.05). These factors were subsequently inputted during the model development. As shown in Table 3 , compared with patients without diabetes, patients with diabetes had a 2.79-fold increase (95%CI = 1.61–4.86) in the risk of being infected. Patients with neurological disease (AOR = 1.93, 95%CI = 1.11–3.35), CVC (AOR = 2.53, 95%CI = 1.39–4.64) or UC (AOR = 2.28, 95%CI = 1.24–4.27) were more likely to be infected. A PCT concentration＞0.5 ng/ml(AOR = 2.03, 95%CI = 1.41–3.82) was associated with increased risk. Cr＜44 umol/L (AOR = 0.40, 95%CI = 0.22–0.71) was a protective factor. An IL-6 concentration < 10 pg/ml might be associated with increased infection risk (AOR = 1.69, 95%CI = 0.97–2.94). Table 3 Univariate and multivariate logistic regression analyses with the stepwise method in the training set (n = 1244). Characteristics Total(%) Univariate analysis Multivariable regression COR (95%CI) P AOR (95%CI) P Gender, male 510(40.99) 1.19(0.68–2.14) 0.54 Age group,＜65year 509(40.92) 0.73(0.40–1.30) 0.30 BMI_level＜30 751(60.37) 0.88(0.35–2.97) 0.81 Hypertension 611(49.12) 0.92(0.53–1.60) 0.76 Diabetes 344(27.65) 4.11(2.36–7.29) 8.09e-07 2.78(1.61–4.86) 0.0002 Tumor 307(24.68) 1.35(0.73–2.40) 0.32 Kidney disease 443(35.61) 1.93(1.11–3.38) 0.02 Neurological disease 389(31.27) 2.07(1.19–3.61) 0.01 1.93(1.11–3.35) 0.02 Invasive ventilation 153(12.29) 3.57(1.91–6.44) < 0.001 Urinary catheter 393(31.59) 4.64(2.62–8.47) 0.0000002 2.28(1.24–4.27) 0.01 Central venous catheter 290(23.31) 5.10 (2.91–9.11) 1.76e-08 2.53(1.39–4.64) 0.002 Operation 243(19.53) 0.92(0.43–1.78) 0.81 ICU admission 77(6.19) 2.44(0.98–5.27) 0.04 IL-6_level＜10 pg/ml 388(31.19) 1.75(1.04–2.94) 0.03 1.69(0.97–2.94) 0.06 CRP_level＜10 ng/ml 589(47.35) 0.35(0.18–0.63) 0.5 ng/ml 1081(86.89) 0.25(0.14–0.43) < 0.001 2.03(1.41–3.82) 0.03 Cr_level＜44 umol/L 907(72.91) 0.29(0.14–0.43) < 0.001 0.40(0.22–0.71) 0.002 WBC_level＜9.5×10 9 /L 988(79.42) 0.63 (0.34–1.22) 0.15 Ne_level < 80% 859(69.05) 0.40(0.24–0.67) 0.0005 Lym_level＜0.2×10 9 /L 6(0.48) 5.71(0.29–39.42) 0.12 ALB_level＜35 g/L 513(41.24) 2.85(1.62–5.20) 0.0004 Hb_level＜120 g/L 601(48.31) 1.15(0.69–1.92) 0.59 Dexamethasone(DXM) 368(29.58) 2.59(1.49–4.52) 0.001 Meprednisone (MEP) 430(34.57) 1.46(0.83–2.55) 0.18 Tocilizumab(TZ) 14(1.12) 1.74(1.00–9.00) 0.60 Length of hospital stay＜7days 263(21.14) 1.09(0.57–1.96) 0.78 Ref: reference 2.3 Random forest Model The RF model was trained using 1244 inpatients and 14 variables. The random forest model yielded an out-of-bag error of 4.98%. As shown in Fig. 2 , the importance of the variables was obtained as follows: using the mean decrease in accuracy as a criterion, CRP_level and Cr_level made the greatest contributions. 3. Model performance and comparison 3.1 Discrimination The two different models achieved comparable performance levels, as shown in Fig. 3 . The AUCROCs for the GLM and RFM were 0.87(95%CI = 0.80–0.94) and 0.88(95%CI = 0.82–0.93), respectively. The RFM slightly outperformed than the GLM. The sensitivities of both models were greater than 80%. Table 4 Statistics and classification matrix of the testing set Models ROC(95%CI) Cutoff TP TN FP FN Sen Spec Acc PPV NPV F1-score GLM 0.87(0.80–0.94) 0.069 18 443 69 4 0.82 0.87 0.86 0.21 0.99 0.33 RFM 0.88(0.82–0.93) 0.023 19 379 133 3 0.86 0.74 0.75 0.13 0.99 0.22 Sen sensitivity, Spec specificity, TN true negative, FN false negative, TP true positive, FP false positive, PPV positive predict value, NPV negative predict value. Sens(Recall) = TP/(TP + FN) Spec = TN/(TN + FP) PPV (Precision) = TP/(TP + FP) Acc=(TP + TN)/(TP + FP + TN + FN) F1-score = 2*(Precision*Recall)/(Precision + Recall) 3.2 Calibration As shown in Fig. 4 , the calibration lines were close to the ideal lines, and a slope of 1 indicated no overfitting. Both models fit well. However, GLM was the optimal model because the S:p of the RFM was greater than that of the RFM (0.883 vs 0.769). 3.3 Decision curve Both models had greater standard net benefits than default strategies across the threshold range. Thus, both models had better utility in supporting clinical decisions and led to the best decisions. Discussion Bacterial/fungal coinfection is a serious complication of COVID-19, especially in the presence of comorbidities, and can lead to a worse prognosis and antibiotic overuse( 20 ). In the present study, of a total of 1778 patients hospitalized with COVID-19, approximately 5% presented with bacterial/fungal coinfections. We has investigated the risk factors associated with bacterial/fungal infections and developed machine learning-based models with robust predictive performance. The algorithm showed that comorbidities (diabetes, neurological diseases), invasive procedures (central venous catheter, urinary catheter), the baseline inflammatory markers levels (IL-6 0.5 ng/ml) and creatinine < 44 umol/L were associated with an increased risk of bacterial/fungal infection. Our models included variables easily obtained from electronic medical databases, which made it easier to identify high-risk inpatients. When the estimated coinfection risk is low, it is recommended to limit or use antibiotics cautiously, whereas high-risk estimates suggest enhancing surveillance or resource reallocation through additional patient care or enhanced disinfection, which could improve the efficiency of hospital infection surveillance( 21 ). Early detection of high-risk patients is beneficial for preventing hospital infection outbreaks, antibiotic overuse, and microbial resistance. Diabetes is related to various infections, especially skin, lower respiratory tract, and urinary tract infections( 22 ). A review( 22 ) suggested that diabetes and its comorbidity may lead to some infectious diseases due to metabolic disturbances. Similarly, Suheda Erener( 23 ) summarized the clinical data on diabetes and COVID-19 and showed that exaggerated immune system inflammation and an excessive synthesis of cytokines may render patients with diabetes vulnerable to infectious diseases. IL-6 which has diverse biological activities is a key cytokine that can modulate homeostasis and inflammation( 24 ). Previous reports( 24 , 25 ) have shown that an acute infection response induces rapid production of IL-6, and activates the host defense mechanism against infection through elevated acute-phase proteins and the immune response. In our study, low levels of IL-6 had significant predictive value for bacterial/fungal infections, where a baseline value of IL-6 10 pg/ml. However, exacerbation synthesis of cytokines, cytokine storm, can deteriorate the patient's clinical conditions( 26 ). Future studies could explore cytokine levels and changes at different stages of bacterial/fungal infection among COVID-19 patients and their impact on prognosis. PCT is a well-known biomarker of bacterial infection and has been proven to be involved in the early recognition of bacterial coinfection in patients with influenza pneumonia. However, the value of PCT in predicting bacterial coinfection in patients with COVID-19 has remained unknown, PCT is a biomarker of disease severity( 27 , 28 ). A study showed that PCT has a high negative predictive value for ruling out community-acquired bacterial coinfection, and a baseline PCT level > 0.5 ng/ml is a predictor of ICU mortality( 29 ). In our study, we found that PCT > 0.5 ng/ml was associated with an increased risk of bacterial coinfection, which might indicate the severity of COVID-19 considering that severely ill patients may be more likely to be infected. A meta-analysis concluded that PCT has limited predictive value for coinfection, but lower PCT levels might indicated a decreased risk of coinfection( 30 ). Several studies have noted that high PCT levels at admission are associated with severe outcomes in critically ill patients( 20 , 31 ). Nonetheless, PCT could be used as a helpful tool to guide antibiotic therapy for COVID-19( 32 ). In line with the findings of previous studies( 2 , 12 ), multivariate logistic analysis indicated that central venous and urinary catheters are associated with increased infection risk. The most common infection source of catheters is intradermal and catheter interface contamination by organisms, which may come from the patient's skin or from healthcare workers’ hands. Patients with catheters have severe disease and lower immunity, so it is harder to defend against bacterial invasion. In our study, these factors were inputted as strong predictors for model development which gained promising results for risk estimates. Discrimination is a traditional performance metric in model evaluation that uses the AUCROC to compare models. In our study, the AUCROCs of the two models exceeded 0.85, which indicated good accuracy. Few studies have drawn calibration curves to evaluate the matching degree between predicted and actual probabilities( 18 ). Our calibration lines are close to the ideal lines with well-calibrated probabilities. The decision curves showed that these models had greater standard net benefits across all risk thresholds, which indicated that early management of high-risk patients could be beneficial according to our models( 19 ). Recent studies have initiated the prediction models to identify bacterial coinfections among CPVID-19 patients. A study( 11 ) in Italy calculated a predictive risk score by assigning a point value according to the β coefficient to classify patients at risk of bacterial coinfection. This intuitive approach may be useful in diagnostic testing and antibiotic use for community-acquired infections. RAWSON T M et al.( 9 ) have demonstrated that a support vector machine (SVM) with 21 blood test variables can accurately predict positive microbiological samples. However, antibiotic therapy or other interventions might influence daily blood test results, and our study avoided this problem because we included blood test results at admission. Our study has several limitations. First, we may underestimate the prevalence of bacterial/fungal infections due to the retrospective study design. Generally, clinicians and IPCs diagnose and report healthcare-associated infection cases, and the number of cases detected partly relies on the extent of their efforts and the sensitivities of surveillance. Second, there was no external testing available to evaluate the transportability and generalizability of the prediction models. Future studies could externally validate and update the models in different settings to apply the models in clinical practice. Conclusions Our results indicate that the machine learning models achieved strong predictive ability and may be effective clinical decision support tools for bacterial/fungal infection surveillance and for guiding antibiotic administration. The GLM suggested that patients with an IL-6 concentration < 10pg/ml are more vulnerable to developing a bacterial/fungal infection. Declarations Ethics approval and consent to participate The study protocol was approved by the Ethics Committee of Nanjing Drum Tower Hospital, Affiliated Hospital of Medical School, Nanjing University (NO.2023-433-02). All participants provided written informed consent after completing the description of the study. Consent for publication Not applicable. Availability of data and materials The datasets used and/or analyzed during the current study are available from the corresponding author upon reasonable request. Competing interests The authors declare that they have no competing interests. Author contributions MW and WL prepared the materials and collected the data. MW analyzed data and wrote the first draft of the manuscript. HW helped to proofread the manuscript. PS supervised the study and made critical revisions to the manuscript. PS analyzed and interpreted patient data regarding risk factors and bacterial/fungal coinfection. All the authors contributed to the study conception and design and approved the submitted version. Acknowledgement We thank all the doctors, laboratory technicians, and project administrators who made contributions to the databases. We are grateful to Huixue Jia from Peking University First Hospital and Jinqi Wang from the Central Hospital of Wuhan for the helpful discussions and critical opinions. Funding This study was supported by the Project of Chinese Hospital Reform and Development Institute, Nanjing University (NDYGN2023040), and the special fund project of Nanjing Drum Tower Hospital Clinical Research (2023-LCYJ-MS-35). References Nasir N, Rehman F, Omair SF. Risk factors for bacterial infections in patients with moderate to severe COVID-19: A case‐control study. J MED VIROL. 2021;93(7):4564–9. Cheng K, He M, Shu Q, Wu M, Chen C, Xue Y. Analysis of the Risk Factors for Nosocomial Bacterial Infection in Patients with COVID-19 in a Tertiary Hospital. Risk Manage Healthc Policy. 2020;13:2593–9. Lansbury L, Lim B, Baskaran V, Lim WS. Co-infections in people with COVID-19: a systematic review and meta-analysis. J Infect. 2020;81(2):266–75. Markovskaya Y, Gavioli EM, Cusumano JA, Glatt AE. Coronavirus disease 2019 (COVID-19): Secondary bacterial infections and the impact on antimicrobial resistance during the COVID-19 pandemic. Antimicrob Stewardship Healthc Epidemiol. 2022;2(1). Kubin CJ, McConville TH, Dietz D, Zucker J, May M, Nelson B et al. Characterization of Bacterial and Fungal Infections in Hospitalized Patients With Coronavirus Disease 2019 and Factors Associated With Health Care-Associated Infections. OPEN FORUM INFECT DI. 2021 2021-06-01;8(6). Gajic I, Jovicevic M, Popadic V, Trudic A, Kabic J, Kekic D, et al. The emergence of multi-drug-resistant bacteria causing healthcare-associated infections in COVID-19 patients: a retrospective multi-centre study. J HOSP INFECT. 2023;137:1–7. Silva A DL, MLA C, CRME V, MBA L, TAPA N. B RBC, Fungal and bacterial coinfections increase mortality of severely ill COVID-19 patients. J HOSP INFECT. 2021. Garcia-Vidal C, Sanjuan G, Moreno-García E, Puerta-Alcalde P, Garcia-Pouton N, Chumbita M, et al. Incidence of co-infections and superinfections in hospitalized patients with COVID-19: a retrospective cohort study. CLIN MICROBIOL INFEC. 2021;27(1):83–8. Rawson TM, Hernandez B, Wilson RC, Ming D, Herrero P, Ranganathan N et al. Supervised machine learning to support the diagnosis of bacterial infection in the context of COVID-19. JAC Antimicrob Resist. [Journal Article]. 2021 2021-03-01;3(1):b2. Vaughn VM, Gandhi TN, Petty LA, Patel PK, Prescott HC, Malani AN et al. Empiric Antibacterial Therapy and Community-onset Bacterial Coinfection in Patients Hospitalized With Coronavirus Disease 2019 (COVID-19): A Multi-hospital Cohort Study. CLIN INFECT DIS. 2021 2021-05-18;72(10):e533–41. Giannella M, Rinaldi M, Tesini G, Gallo M, Cipriani V, Vatamanu O, et al. Predictive model for bacterial co-infection in patients hospitalized for COVID-19: a multicenter observational cohort study. Infection. 2022;50(5):1243–53. Novacescu AN, Buzzi B, Bedreag O, Papurica M, Rogobete AF, Sandesc D et al. Bacterial and Fungal Superinfections in COVID-19 Patients Hospitalized in an Intensive Care Unit from Timișoara, Romania. INFECT DRUG RESIST. 2022 2022-01-01;15:7001–14. Cheng K, He M, Shu Q, Wu M, Chen C, Xue Y. Analysis of the Risk Factors for Nosocomial Bacterial Infection in Patients with COVID-19 in a Tertiary Hospital. 2020;Vol. 13:2593–9. Moreno-García E, Puerta-Alcalde P, Letona L, Meira F, Dueñas G, Chumbita M,. Bacterial co-infection at hospital admission in patients with COVID-19. INT J INFECT DIS. 2022;118:197–202. Moreno-Torres V, de Mendoza C, de la Fuente S, Sánchez E, Martínez-Urbistondo M, Herráiz J,. Bacterial infections in patients hospitalized with COVID-19. INTERN EMERG MED. 2022;17(2):431–8. Kumar G, Adams A, Hererra M, Rojas ER, Singh V, Sakhuja A,. Predictors and outcomes of healthcare-associated infections in COVID-19 patients.INT J INFECT DIS. 2021;104:287–92. GAO Jing*, CHEN Yong, WANG Pengfei, .Construction and validation of the prediction model for critical COVID-19 combined with bacterial or fungal infection.Infect Dis Info, 36, 3, June 30, 2023 Chen PC, Liu Y, Peng L. How to develop machine learning models for healthcare. NAT MATER. 2019 2019-01-01;18(5):410–4. Van Calster B, Wynants L, Verbeek JFM, Verbakel JY, Christodoulou E, Vickers AJ,. Reporting and Interpreting Decision Curve Analysis: A Guide for Investigators.EUR UROL. 2018;74(6):796–804. Alnimr AM, Alshahrani MS, Alwarthan S, AlQahtani SY, Hassan AA, BuMurah NN,. Bacterial and Fungal Coinfection in Critically Ill COVID-19 Cases and Predictive Role of Procalcitonin During the First Wave at an Academic Health Center.J Epidemiol Glob Health. [Journal Article; Review]. 2022 2022-06-01;12(2):188–95. Cho SY, Kim Z, Chung DR, Cho BH, Chung MJ, Kim JH,. Development of machine learning models for the surveillance of colon surgical site infections.The Journal of hospital infection. [Journal Article]. 2023 2023-04-22. Akash M, Rehman K, Fiayyaz F, Sabir S, Khurshid M. Diabetes-associated infections: development of antimicrobial resistance and possible treatment strategies. ARCH MICROBIOL. [Journal Article; Review]. 2020 2020-07-01;202(5):953–65. Erener S. Diabetes, infection risk and COVID-19. MOL METAB. [Journal Article; Research Support, Non-U.S. Gov't; Review]. 2020 2020-09-01;39:101044. Kishimoto T, Kang S. IL-6 Revisited: From Rheumatoid Arthritis to CAR T Cell Therapy and COVID-19. ANNU REV IMMUNOL. [Journal Article; Research Support, Non-U.S. Gov't; Review]. 2022 2022-04-26;40:323 – 48. Heinrich PC, Castell JV, Andus T. Interleukin-6 and the acute phase response.BIOCHEM J. [Journal Article; Review]. 1990 1990-02-01;265(3):621–36. Arjmand B, Alavi-Moghadam S, Sarvari M, Rezaei-Tavirani M, Rezazadeh-Mafi A, Arjmand R,. Critical roles of cytokine storm and bacterial infection in patients with COVID-19: therapeutic potential of mesenchymal stem cells.INFLAMMOPHARMACOLOGY. [Journal Article; Review]. 2023 2023-02-01;31(1):171–206. Heer RS, Mandal AKJ, Szawarski P, Missouris CG. Procalcitonin is a biomarker for disease severity rather than bacterial co-infection in COVID-19.EUR J EMERG MED. 2022;29(4):315. Vazzana N, Dipaola F, Ognibene S. Procalcitonin and secondary bacterial infections in COVID-19: association with disease severity and outcomes. ACTA CLIN BELG. [Journal Article; Meta-Analysis]. 2022 2022-04-01;77(2):268–72. Carbonell R, Urgelés S, Salgado M, Rodríguez A, Reyes LF, Fuentes YV,. Negative predictive value of procalcitonin to rule out bacterial respiratory co-infection in critical covid-19 patients.J Infect. [Journal Article; Research Support, Non-U.S. Gov't]. 2022 2022-10-01;85(4):374–81. Wei S, Wang L, Lin L, Liu X. Predictive values of procalcitonin for coinfections in patients with COVID-19: a systematic review and meta-analysis.VIROL J. [Journal Article; Meta-Analysis; Research Support, Non-U.S. Gov't; Review; Systematic Review]. 2023 2023-05-08;20(1):92. Lugito N. Is procalcitonin a part of human immunological response to SARS-CoV-2 infection or just a marker of bacterial coinfection? CURR RES TRANSL MED. [Letter]. 2021 2021-05-01;69(2):103289. Wolfisberg S, Gregoriano C, Schuetz P. Procalcitonin for individualizing antibiotic treatment: an update with a focus on COVID-19. Crit Rev Clin Lab Sci. [Journal Article; Review]. 2022 2022-01-01;59(1):54–65. Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 14 Apr, 2024 Read the published version in Antimicrobial Resistance & Infection Control → Version 1 posted Editorial decision: Revision requested 07 Mar, 2024 Reviews received at journal 16 Feb, 2024 Reviewers agreed at journal 27 Jan, 2024 Reviewers agreed at journal 27 Jan, 2024 Reviewers invited by journal 23 Jan, 2024 Editor assigned by journal 11 Jan, 2024 Submission checks completed at journal 10 Jan, 2024 First submitted to journal 09 Jan, 2024 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-3847614","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":266211135,"identity":"7543f0c6-d08b-4cab-952a-4df2d8540cbe","order_by":0,"name":"Min Wang","email":"","orcid":"","institution":"Nanjing Drum Tower Hospital","correspondingAuthor":false,"prefix":"","firstName":"Min","middleName":"","lastName":"Wang","suffix":""},{"id":266211136,"identity":"8588d352-71b7-4934-b404-1537d6051def","order_by":1,"name":"Wenjuan Li","email":"","orcid":"","institution":"Nanjing Drum Tower Hospital","correspondingAuthor":false,"prefix":"","firstName":"Wenjuan","middleName":"","lastName":"Li","suffix":""},{"id":266211137,"identity":"02601dbf-316b-4e4d-8182-d5292264a3b3","order_by":2,"name":"Hui Wang","email":"","orcid":"","institution":"Nanjing Drum Tower Hospital","correspondingAuthor":false,"prefix":"","firstName":"Hui","middleName":"","lastName":"Wang","suffix":""},{"id":266211139,"identity":"cdbdbd46-13bc-4d2c-8265-417201a9dd45","order_by":3,"name":"Peixin song","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7UlEQVRIie3RMQrCMBSA4ZRAXUTXVwr1CpGCpeBhEryAk2NVCpl6gHoHByd1jHRwqbpm0y7dBEEQ3EwVdEsdBfMveUM+khCETKafzJog+hywQFCt4nti02/JuyZ5rXUkaMQcinXkBe357RRy5LUkta5DDQmTTUxYnvlhel4RhyPfkRS7qYYQyaYnxgVbyN0SFFEDtXFTR47FRDAeqZ15WZFxPZFWdQpmi0NiV4SSOhImTL2FZz6Rdg9gD91ZXsSujgSNbenceeSRQ1a6MOp3WtvB5qq92HsCijA8P1N9rq4PaQtkXbR7TSaT6V97ANDmT0SDZm7lAAAAAElFTkSuQmCC","orcid":"","institution":"Nanjing Drum Tower Hospital","correspondingAuthor":true,"prefix":"","firstName":"Peixin","middleName":"","lastName":"song","suffix":""}],"badges":[],"createdAt":"2024-01-09 07:59:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3847614/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3847614/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s13756-024-01392-7","type":"published","date":"2024-04-14T19:49:05+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":49492847,"identity":"c20b92bb-6c24-4d7e-b794-3b26916a65a9","added_by":"auto","created_at":"2024-01-11 18:32:13","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":165572,"visible":true,"origin":"","legend":"\u003cp\u003eFlowchart of study participant selection and model development and validation.\u003c/p\u003e","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-3847614/v1/f7afa3560fb315ea8ebc4942.png"},{"id":49491982,"identity":"ec05cb53-8958-4eeb-9a8a-3895c6bcb204","added_by":"auto","created_at":"2024-01-11 18:24:13","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":22309,"visible":true,"origin":"","legend":"\u003cp\u003eVariable importance for the random forest model (RFM). SZB, kidney disease; SJB, neurological disease; ICU, ICU admission; ALB_level, albumin level; Cr_level, creatinine level; Ne_level, neutrophil level; CVC, central venous catheter; UC, urinary catheter; IV, invasive ventilation; DXM, dexamethasone.\u003c/p\u003e","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-3847614/v1/90fdca31b7c38f8e6ce122dc.png"},{"id":49491980,"identity":"db0ddea5-6ead-48e0-a6ce-916effa05620","added_by":"auto","created_at":"2024-01-11 18:24:13","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":19371,"visible":true,"origin":"","legend":"\u003cp\u003ePerformance of different machine learning models(the testing set, n=534)\u003c/p\u003e","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-3847614/v1/cfc8535cdccf492b6ee57a5c.png"},{"id":49491981,"identity":"90b9f8b2-d4a8-4207-a62e-94e8b5deb1a5","added_by":"auto","created_at":"2024-01-11 18:24:13","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":26396,"visible":true,"origin":"","legend":"\u003cp\u003eCalibration curves of different machine learning models (the testing set, n=534).\u003c/p\u003e","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-3847614/v1/e10d4cdf53b4079300e60b00.png"},{"id":49491984,"identity":"cb4e7b1a-207e-4f87-8a5f-2f1e2a9beff1","added_by":"auto","created_at":"2024-01-11 18:24:13","extension":"jpeg","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":199280,"visible":true,"origin":"","legend":"\u003cp\u003eDecision curves for the default strategies and for GLM and RFM(the testing set, n=534).\u003c/p\u003e","description":"","filename":"floatimage5.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-3847614/v1/ac245fce5c9f6fdbcf50ee70.jpeg"},{"id":54656462,"identity":"c6388a0a-ba67-464b-87b2-394ee7f8d5b7","added_by":"auto","created_at":"2024-04-14 19:49:11","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":940188,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3847614/v1/8e9adb97-8c8c-40da-8c40-4b716c1cb77b.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Development and validation of machine learning-based models for predicting healthcare-associated bacterial/fungal infections among COVID-19 inpatients: a retrospective cohort study","fulltext":[{"header":"Background","content":"\u003cp\u003eRespiratory virus infections are associated with an increased risk of bacterial/fungal infections, especially in lower respiratory tract infections(\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e, \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e). Current studies have reported that the prevalence of healthcare-associated bacterial/fungal infections in patients with COVID-19 ranges from 3.6\u0026ndash;32%(\u003cspan additionalcitationids=\"CR3 CR4 CR5\" citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e). Researchers(\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e, \u003cspan additionalcitationids=\"CR7\" citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e)have shown that COVID-19 and bacterial/fungal coinfections in those patients might contribute to worse outcomes, such as prolonged hospitalization and a higher mortality rate.\u003c/p\u003e \u003cp\u003eThe long-term impacts of viral and bacterial/fungal coinfections on antimicrobial resistance are severe public problems(\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e). It is difficult for clinicians to identify coinfections early because of similar symptoms and signs, thus leading to a high rate of inappropriate prescription(\u003cspan additionalcitationids=\"CR11\" citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e). Early empiric antibiotic use varied from 27\u0026ndash;84% across different hospitals(\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e). Two multicenter cohort studies(\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e, \u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e) showed that the proportions of bacterial coinfection were lower than 10%, while the proportions of early empirical antibiotics were as high as 60%. However, without bacterial coinfections, antibiotic overuse not only does not benefit patients but also accelerates the development of antimicrobial resistance.\u003c/p\u003e \u003cp\u003ePrevious studies(\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e, \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e, \u003cspan additionalcitationids=\"CR13\" citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e) have focused on the characteristics and risk factors for bacterial coinfection in patients with COVID-19. In the literature, several predictors, such as PCT, CRP, steroid use, invasive ventilation, central venous catheter, urinary catheter, tocilizumab, length of stay, ICU admission, comorbidity, played significant roles in discriminating healthcare-associated bacterial coinfections(\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e, \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e, \u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e, \u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e, \u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e, \u003cspan additionalcitationids=\"CR15\" citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eRecent studies(\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e, \u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e, \u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e) have used scientific statistical methods to estimate the risk of healthcare-associated bacterial coinfections in COVID-19 patients, instead of limiting the identification of risk factors. Estimating the probability of an individual developing healthcare-associated infections could help guide intervention earlier through patient care, microbiological testing and therapeutic measures. Therefore, establishing good predictive models has practical significance for clinical work and is beneficial for identifying high-risk patients and preventing and controlling them precisely.\u003c/p\u003e \u003cp\u003eAs machine learning (ML) is used for disease diagnosis or prognosis prediction, it is feasible to identify patients at high risk of bacterial coinfections(\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e). Compared to traditional models, machine learning models have faster processors and smarter algorithms. Rapid progress in machine learning has provided opportunities for improved patient healthcare(\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e). In this retrospective cohort study, we investigated the risk factors and established different ML models to predict the risk of healthcare-associated bacterial/fungal coinfections among inpatients with COVID-19.\u003c/p\u003e"},{"header":"Method","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003eInclusion and exclusion criteria\u003c/h2\u003e \u003cp\u003e Inpatients who tested positive for COVID-19 according to nasopharyngeal swab PCR between January 1 and July 31, 2023 in a tertiary hospital in China were included. This hospital serves a population of more than nine million people and provides tertiary referral services to the surrounding regions. The exclusion criteria were as follows: (\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e) patients under 18 years of age, (\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e) had a hospital stay less than three days, and (\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e) repeated patients.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003eStudy design and data collection\u003c/h2\u003e \u003cp\u003eIn this retrospective, single-center cohort study, data including demographic information (age, sex, height, weight), comorbidity information (diabetes, hypertension, neurological diseases), and clinical records (operation history, invasive ventilation, urinary catheter), and laboratory results at admission (blood cell count, PCT, IL-6, creatinine) were collected directly from an electronic health record database. Clinicians and prevention and control professionals (IPCs) diagnosed and reported healthcare-associated bacterial/fungal coinfections under a healthcare-associated infection surveillance system and they reviewed the medical records of all patients with positive microbiological results to assess clinical significance (infection,colonization, or contamination).\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003eData processing and Statistical analysis\u003c/h2\u003e \u003cp\u003eAll the data processing and analysis were conducted using R (version 4.3.0). Missing value were processed for weight (n\u0026thinsp;=\u0026thinsp;477,26.83%), height (n\u0026thinsp;=\u0026thinsp;387,27.77%), white blood cell count (n\u0026thinsp;=\u0026thinsp;6,0.34%), PCT(n\u0026thinsp;=\u0026thinsp;481,27.05%), IL-6(n\u0026thinsp;=\u0026thinsp;561,31.5%), neutrophil percent(n\u0026thinsp;=\u0026thinsp;6,0.34%), lymphocyte count (n\u0026thinsp;=\u0026thinsp;9,0.51%), CRP(n\u0026thinsp;=\u0026thinsp;66,3.71%), creatinine(n\u0026thinsp;=\u0026thinsp;82,4.61%), hemoglobin(n\u0026thinsp;=\u0026thinsp;9,0.51%), albumin (n\u0026thinsp;=\u0026thinsp;40,2.25%), glucose (n\u0026thinsp;=\u0026thinsp;6,0.34%) according to multiple imputation method and were conducted for five imputations.\u003c/p\u003e \u003cp\u003eContinuous variables are reported as the medians and inter-quartile ranges (IQRs) and were compared using the Kruskal-Wallis test. Categorical variables are reported as counts and percentages and were compared using the Chi-sq or Fisher\u0026rsquo;s exact test. We conducted univariate and stepwise multivariate logistic regression analyses to investigate risk factors for HA bacterial/fungal infection. Factors with a P-value less than 0.05 were independently associated with HA infections. Adjusted odds ratios (AORs) and 95% confidence intervals (95%CIs) were estimated.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003eModel development and internal validation\u003c/h2\u003e \u003cp\u003eWe randomly divided all the samples into a training set and a testing set at a ratio of 7:3. The training set was used to screen variables and develop models, while the testing set was used for model evaluation. We selected variables for the model development which were statistically significant in our univariate analysis. The models included 14 candidate predictors, as follows: diabetes, kidney disease, neurological disease, ICU admission, PCT_level, albumin (ALB_level), creatinine (Cr_level), IL-6_level, CRP_level, neutrophil (Ne_level), central venous catheter (CVC), urinary catheter (UC), invasive ventilation (IV), and dexamethasone (DXM). The variance inflation factors (VIF) were calculated to assess the multicollinearity of the predictors. As all the predictors had a VIF less than 2, indicating no multicollinearity, all the predictors were included in the model development.\u003c/p\u003e \u003cp\u003eA random forest model was established (ntree\u0026thinsp;=\u0026thinsp;500, mtry\u0026thinsp;=\u0026thinsp;4) and the importance of the variables was determined. Our study compared the discrimination of models by the area under the receiver operating curve (AUCROC). The calibration slopes were calculated to check the risk of overfitting. Decision curve analyses were performed to evaluate whether the risk models improved clinical decision-making(\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e).\u003c/p\u003e \u003c/div\u003e"},{"header":"Results","content":"\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003e1. Baseline characteristics\u003c/h2\u003e \u003cp\u003eA total of 1946 inpatients were diagnosed with laboratory-confirmed with COVID-19 between January 1 and July 31, 2023. As shown in the Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e, 1778 eligible inpatients were enrolled in this study. The median age of the patients was 69 years (interquartile rage (IQR), 56\u0026ndash;80 years), and 1043 were male (58.66%). The Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e shows the difference in baseline characteristics between the HA infection group and the Non-HA infection group. Eighty-four (4.72%) patients developed healthcare-associated bacterial/fungal infections, 75 of whom were bacterial infections and 9 of whom had fungal infections. The most common bacterial strain isolated was \u003cem\u003eklebsiella pneumoniae\u003c/em\u003e which was found in 18 patients and the main infection site was the lower respiratory tract.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eDemographic characteristics, comorbidities, and laboratory test results for patients with HA bacterial/fungal infections and non-HA infections at baseline.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"6\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCharacteristics\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTotal\u003c/p\u003e \u003cp\u003e(N\u0026thinsp;=\u0026thinsp;1778)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eHA infection\u003c/p\u003e \u003cp\u003e(N\u0026thinsp;=\u0026thinsp;84)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eNon-HA infection (N\u0026thinsp;=\u0026thinsp;1694)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003ec\u003csup\u003e2/W\u003c/sup\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\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\u003eGender [n,%]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.08\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.78\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003emale\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1043(58.66)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e51(60.71)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e992(58.56)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003efemale\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e735(41.34)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e33(39.29)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e702(43.44)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAge, year [M,IQR]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e69(56,80)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e75(60,86.25)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e68(56,79)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e54978\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBMI [M,IQR]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e23.39(21.20,25.95)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e22.59(19.82,24.34)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e23.43(21.25,26.03)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e27744\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.04\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHypertension [n,%]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1.34\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.25\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e896(50.39)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e48(57.14)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e848(50.06)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e882(46.61)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e36(42.86)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e846(49.94)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDiabetes [n,%]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e33.93\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e470(26.43)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e47(55.95)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e423(24.97)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1308(73.56)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e37(44.05)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1271(75.03)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTumor [n,%]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.59\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.44\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e455(25.59)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e25(29.76)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e430(25.38)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1323(74.41)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e59(70.24)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1264(74.62)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eKidney disease [n,%]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e8.47\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.004\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e655(36.84)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e44(52.38)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e611(36.07)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1123(63.16)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e40(47.62)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1083(63.93)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNeurological disease [n,%]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e24.14\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e571(32.11)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e48(57.14)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e523(30.87)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1207(67.89)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e36(42.86)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1171(69.13)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOperation[n,%]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.09\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.76\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e351(19.74)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e15(17.86)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e336(19.83)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1427(80.26)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e69(82.14)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1358(80.17)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eICU admission [n,%]:\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e11.24\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e111(6.24)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e13(15.48)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e98(5.79)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1667(93.76)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e71(84.52)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1596(94.21)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eTreatments before coinfections\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eInvasive ventilation (IV)[n,%]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e49.65\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e224(12.60)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e32(38.10)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e192(11.33)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1554(87.40)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e52(61.90)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1502(88.67)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eUrinary catheter (UC)[n,%]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e58.08\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e566(31.83)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e59(70.24)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e507(29.93)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1212(68.17)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e25(29.76)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1187(70.07)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCentral venous catheter(CVC)[n,%]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e53.34\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e\u003cb\u003e\u0026lt;\u0026thinsp;0.001\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e433(24.35)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e49(58.33)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e384(22.67)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1345(75.65)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e35(41.67)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1310(77.33)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDexamethasone (DXM)[n,%]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e21.69\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e\u003cb\u003e\u0026lt;\u0026thinsp;0.001\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e537(30.20)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e45(53.57)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e492(29.04)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1241(69.80)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e39(46.43)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1202(70.96)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMeprednisone(MEP) [n,%]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e2.33\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.13\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e594(33.41)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e35(41.67)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e559(33.00)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1184(66.59)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e49(58.33)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1135(67.00)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTocilizumab\u003csup\u003e**\u003c/sup\u003e(TZ)[n,%]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e21(1.18)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1(1.19)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e20(1.18)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1757(98.82)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e83(98.81)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1674(98.81)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eLaboratory test results on admission\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eWhite blood cell count(WBC)\u003csup\u003e*\u003c/sup\u003e, 10\u003csup\u003e9\u003c/sup\u003e/L[M,IQR]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e7.56(4.7,8.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7.15(5.5,10.20)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e6.1(4.7,8.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e56462\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e\u003cb\u003e0.002\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNeutrophil percent(Ne) \u003csup\u003e*\u003c/sup\u003e,% [M,IQR]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e70.21(59.80,82.20)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e79.7(67.6,90.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e70.6(59.5,81.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e47654\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e\u003cb\u003e3.818e-07\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePCT\u003csup\u003e*\u003c/sup\u003e, ng/ml[M,IQR]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.395(0.036,0.204)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.14(0.068,1.503)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.071(0.036,0.196)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e34373\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e\u003cb\u003e2.533e-06\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eIL-6\u003csup\u003e*\u003c/sup\u003e,pg/ml[M,IQR]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e22.52(7.49,54.31)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e18.02(5.538,42.815)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e22.67(7.69,56.10)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e33935\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.14\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCRP\u003csup\u003e*\u003c/sup\u003e, mg/L[M,IQR]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e12.10(3.9,34.53)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e10.9(3.9,45.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e50.3(10.5,114.15)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e44715\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e\u003cb\u003e1.889e-07\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAlbumin\u003csup\u003e*\u003c/sup\u003e(ALB), g/L [M,IQR]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e35.7(32.42,39.20)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e33(29.1,35.875)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e36.3(32.6,39.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e94897\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e\u003cb\u003e1.452e-08\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLymphocyte count(Lym)\u003csup\u003e*\u003c/sup\u003e, [M,IQR]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2.198(0.7,1.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.9(0.575,1.325)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.1(0.7,1.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e83667\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e\u003cb\u003e0.005\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCreatinine(Cr)\u003csup\u003e*\u003c/sup\u003e, umol/L[M,IQR]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e34.41(4,47.88)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e50.60(12.55,114.15)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e10.9(3.9,45.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e42972\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e\u003cb\u003e3.622e-08\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHemoglobin(Hb)\u003csup\u003e*\u003c/sup\u003e, g/L [M,IQR]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e117.1(104,133)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e112.5(95.75,126.50)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e120(104,133)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e80214\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e\u003cb\u003e0.04\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGlucose(Glu)\u003csup\u003e*\u003c/sup\u003e, mmol/L [M,IQR]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e6.584(4.52,7.29)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e6.705(5.01,10.69)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e5.26(4.5,7.14)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e48508\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e\u003cb\u003e5.007e-06\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLength of hospital stay\u003csup\u003e*\u003c/sup\u003e, day [M,IQR]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e13.12(7,16)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e13(6,19)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e11(7,16)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e68409\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.55\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eThe bold values indicate that these factors were statistically significant.\u003c/p\u003e \u003cp\u003eM: median, IQR: interquartile range.\u003c/p\u003e \u003cp\u003e* The statistical analysis were performed with the Kruskal-Wallis test.\u003c/p\u003e \u003cp\u003e** P-value calculated by Fisher\u0026rsquo;s exact probability method.\u003c/p\u003e \u003cp\u003eAccording to random sampling results, a total of 1244 patients in the training set had 62 HA infections, while 534 patients in the testing set had 22 HA infections. There was no significant difference in the HA infection rate between the two groups (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.51).\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\u003eSampling results for the training set and testing set.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"6\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"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 \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDatasets\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eHA infection\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eNon-HA infection\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eTotal\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003ec\u003csup\u003e2\u003c/sup\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\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\u003eThe training set\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e62(4.98%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1182(95.02%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e1244(69.97%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.44\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.51\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eThe testing set\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e22(4.12%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e512(95.88%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e534(30.03%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTotal\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e84(4.72%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1694(95.28%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e1778(100.00%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec9\" class=\"Section2\"\u003e \u003ch2\u003e2. Model development\u003c/h2\u003e \u003cdiv id=\"Sec10\" class=\"Section3\"\u003e \u003ch2\u003e2.1 General linear model\u003c/h2\u003e \u003cp\u003eThe result of the ANOVA test (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.66) indicated no significant difference between the full and stepwise models, and the AIC of the stepwise model was lower (417.22) than that of the full model (426.17). Thus, the stepwise logistic regression model was chosen as the final general linear model and included 7 predictors, as shown in Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e.\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv id=\"Sec11\" class=\"Section2\"\u003e \u003ch2\u003e2.2 Independent risk factors\u003c/h2\u003e \u003cp\u003eAccording to the univariate analysis, 14 variables were associated with healthcare-associated bacterial/fungal infection, including diabetes, kidney disease (SZB), neurological disease (SJB), invasive ventilation (IV), urinary catheter (UC), central venous catheter (CVC), ICU admission, IL-6_level\u0026thinsp;\u0026lt;\u0026thinsp;10 pg/ml, CRP_level\u0026thinsp;\u0026lt;\u0026thinsp;10 ng/ml, PCT_level\u0026thinsp;\u0026gt;\u0026thinsp;0.5 ng/ml, Cr_level\u0026thinsp;\u0026lt;\u0026thinsp;44 umol/L, Ne_level\u0026thinsp;\u0026lt;\u0026thinsp;80%, Lym_level\u0026thinsp;\u0026lt;\u0026thinsp;0.2\u0026times;10\u003csup\u003e9\u003c/sup\u003e/L, and dexamethasone (DXM) (P\u0026thinsp;\u0026lt;\u0026thinsp;0.05). These factors were subsequently inputted during the model development.\u003c/p\u003e \u003cp\u003eAs shown in Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e, compared with patients without diabetes, patients with diabetes had a 2.79-fold increase (95%CI\u0026thinsp;=\u0026thinsp;1.61\u0026ndash;4.86) in the risk of being infected. Patients with neurological disease (AOR\u0026thinsp;=\u0026thinsp;1.93, 95%CI\u0026thinsp;=\u0026thinsp;1.11\u0026ndash;3.35), CVC (AOR\u0026thinsp;=\u0026thinsp;2.53, 95%CI\u0026thinsp;=\u0026thinsp;1.39\u0026ndash;4.64) or UC (AOR\u0026thinsp;=\u0026thinsp;2.28, 95%CI\u0026thinsp;=\u0026thinsp;1.24\u0026ndash;4.27) were more likely to be infected. A PCT concentration＞0.5 ng/ml(AOR\u0026thinsp;=\u0026thinsp;2.03, 95%CI\u0026thinsp;=\u0026thinsp;1.41\u0026ndash;3.82) was associated with increased risk. Cr＜44 umol/L (AOR\u0026thinsp;=\u0026thinsp;0.40, 95%CI\u0026thinsp;=\u0026thinsp;0.22\u0026ndash;0.71) was a protective factor. An IL-6 concentration\u0026thinsp;\u0026lt;\u0026thinsp;10 pg/ml might be associated with increased infection risk (AOR\u0026thinsp;=\u0026thinsp;1.69, 95%CI\u0026thinsp;=\u0026thinsp;0.97\u0026ndash;2.94).\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\u003eUnivariate and multivariate logistic regression analyses with the stepwise method in the training set (n\u0026thinsp;=\u0026thinsp;1244).\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=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"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\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eCharacteristics\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eTotal(%)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e \u003cp\u003eUnivariate analysis\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e \u003cp\u003eMultivariable regression\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eCOR (95%CI)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eAOR (95%CI)\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\u003eGender, male\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e510(40.99)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.19(0.68\u0026ndash;2.14)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.54\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAge group,＜65year\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e509(40.92)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.73(0.40\u0026ndash;1.30)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.30\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBMI_level＜30\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e751(60.37)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.88(0.35\u0026ndash;2.97)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.81\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHypertension\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e611(49.12)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.92(0.53\u0026ndash;1.60)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.76\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDiabetes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e344(27.65)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e4.11(2.36\u0026ndash;7.29)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cb\u003e8.09e-07\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e2.78(1.61\u0026ndash;4.86)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.0002\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTumor\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e307(24.68)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.35(0.73\u0026ndash;2.40)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.32\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eKidney disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e443(35.61)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.93(1.11\u0026ndash;3.38)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cb\u003e0.02\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNeurological disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e389(31.27)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2.07(1.19\u0026ndash;3.61)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cb\u003e0.01\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1.93(1.11\u0026ndash;3.35)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.02\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eInvasive ventilation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e153(12.29)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3.57(1.91\u0026ndash;6.44)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cb\u003e\u0026lt;\u0026thinsp;0.001\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eUrinary catheter\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e393(31.59)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e4.64(2.62\u0026ndash;8.47)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cb\u003e0.0000002\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e2.28(1.24\u0026ndash;4.27)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.01\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCentral venous catheter\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e290(23.31)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e5.10 (2.91\u0026ndash;9.11)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cb\u003e1.76e-08\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e2.53(1.39\u0026ndash;4.64)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.002\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOperation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e243(19.53)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.92(0.43\u0026ndash;1.78)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.81\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eICU admission\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e77(6.19)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2.44(0.98\u0026ndash;5.27)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cb\u003e0.04\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eIL-6_level＜10 pg/ml\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e388(31.19)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.75(1.04\u0026ndash;2.94)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cb\u003e0.03\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1.69(0.97\u0026ndash;2.94)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.06\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCRP_level＜10 ng/ml\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e589(47.35)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.35(0.18\u0026ndash;0.63)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cb\u003e\u0026lt;\u0026thinsp;0.001\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePCT_level\u0026thinsp;\u0026gt;\u0026thinsp;0.5 ng/ml\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1081(86.89)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.25(0.14\u0026ndash;0.43)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cb\u003e\u0026lt;\u0026thinsp;0.001\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e2.03(1.41\u0026ndash;3.82)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.03\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCr_level＜44 umol/L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e907(72.91)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.29(0.14\u0026ndash;0.43)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cb\u003e\u0026lt;\u0026thinsp;0.001\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.40(0.22\u0026ndash;0.71)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.002\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eWBC_level＜9.5\u0026times;10\u003csup\u003e9\u003c/sup\u003e/L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e988(79.42)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.63 (0.34\u0026ndash;1.22)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNe_level\u0026thinsp;\u0026lt;\u0026thinsp;80%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e859(69.05)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.40(0.24\u0026ndash;0.67)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cb\u003e0.0005\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLym_level＜0.2\u0026times;10\u003csup\u003e9\u003c/sup\u003e/L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e6(0.48)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e5.71(0.29\u0026ndash;39.42)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.12\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eALB_level＜35 g/L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e513(41.24)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2.85(1.62\u0026ndash;5.20)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cb\u003e0.0004\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHb_level＜120 g/L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e601(48.31)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.15(0.69\u0026ndash;1.92)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.59\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDexamethasone(DXM)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e368(29.58)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2.59(1.49\u0026ndash;4.52)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cb\u003e0.001\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMeprednisone (MEP)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e430(34.57)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.46(0.83\u0026ndash;2.55)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.18\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTocilizumab(TZ)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e14(1.12)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.74(1.00\u0026ndash;9.00)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.60\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLength of hospital stay＜7days\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e263(21.14)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.09(0.57\u0026ndash;1.96)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.78\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"7\"\u003eRef: reference\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec12\" class=\"Section2\"\u003e \u003ch2\u003e2.3 Random forest Model\u003c/h2\u003e \u003cp\u003eThe RF model was trained using 1244 inpatients and 14 variables. The random forest model yielded an out-of-bag error of 4.98%. As shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e, the importance of the variables was obtained as follows: using the mean decrease in accuracy as a criterion, CRP_level and Cr_level made the greatest contributions.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec13\" class=\"Section2\"\u003e \u003ch2\u003e3. Model performance and comparison\u003c/h2\u003e \u003cdiv id=\"Sec14\" class=\"Section3\"\u003e \u003ch2\u003e3.1 Discrimination\u003c/h2\u003e \u003cp\u003eThe two different models achieved comparable performance levels, as shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e. The AUCROCs for the GLM and RFM were 0.87(95%CI\u0026thinsp;=\u0026thinsp;0.80\u0026ndash;0.94) and 0.88(95%CI\u0026thinsp;=\u0026thinsp;0.82\u0026ndash;0.93), respectively. The RFM slightly outperformed than the GLM. The sensitivities of both models were greater than 80%.\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\u003eStatistics and classification matrix of the testing set\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"13\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"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 \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c10\" colnum=\"10\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c11\" colnum=\"11\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c12\" colnum=\"12\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c13\" colnum=\"13\"\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\u003eROC(95%CI)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eCutoff\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eTP\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eTN\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eFP\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003eFN\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c8\"\u003e \u003cp\u003eSen\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c9\"\u003e \u003cp\u003eSpec\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c10\"\u003e \u003cp\u003eAcc\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c11\"\u003e \u003cp\u003ePPV\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c12\"\u003e \u003cp\u003eNPV\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c13\"\u003e \u003cp\u003eF1-score\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGLM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.87(0.80\u0026ndash;0.94)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.069\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e18\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e443\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e69\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.82\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.87\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e \u003cp\u003e0.86\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e \u003cp\u003e0.21\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e \u003cp\u003e0.99\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c13\"\u003e \u003cp\u003e0.33\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRFM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.88(0.82\u0026ndash;0.93)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.023\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e19\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e379\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e133\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.86\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.74\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e \u003cp\u003e0.75\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e \u003cp\u003e0.13\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e \u003cp\u003e0.99\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c13\"\u003e \u003cp\u003e0.22\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eSen sensitivity, Spec specificity, TN true negative, FN false negative, TP true positive, FP false positive, PPV positive predict value, NPV negative predict value.\u003c/p\u003e \u003cp\u003eSens(Recall)\u0026thinsp;=\u0026thinsp;TP/(TP\u0026thinsp;+\u0026thinsp;FN)\u003c/p\u003e \u003cp\u003eSpec\u0026thinsp;=\u0026thinsp;TN/(TN\u0026thinsp;+\u0026thinsp;FP)\u003c/p\u003e \u003cp\u003ePPV (Precision)\u0026thinsp;=\u0026thinsp;TP/(TP\u0026thinsp;+\u0026thinsp;FP)\u003c/p\u003e \u003cp\u003eAcc=(TP\u0026thinsp;+\u0026thinsp;TN)/(TP\u0026thinsp;+\u0026thinsp;FP\u0026thinsp;+\u0026thinsp;TN\u0026thinsp;+\u0026thinsp;FN)\u003c/p\u003e \u003cp\u003eF1-score\u0026thinsp;=\u0026thinsp;2*(Precision*Recall)/(Precision\u0026thinsp;+\u0026thinsp;Recall)\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv id=\"Sec15\" class=\"Section2\"\u003e \u003ch2\u003e3.2 Calibration\u003c/h2\u003e \u003cp\u003eAs shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e, the calibration lines were close to the ideal lines, and a slope of 1 indicated no overfitting. Both models fit well. However, GLM was the optimal model because the S:p of the RFM was greater than that of the RFM (0.883 vs 0.769).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec16\" class=\"Section2\"\u003e \u003ch2\u003e3.3 Decision curve\u003c/h2\u003e \u003cp\u003eBoth models had greater standard net benefits than default strategies across the threshold range. Thus, both models had better utility in supporting clinical decisions and led to the best decisions.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e"},{"header":"Discussion","content":"\u003cp\u003eBacterial/fungal coinfection is a serious complication of COVID-19, especially in the presence of comorbidities, and can lead to a worse prognosis and antibiotic overuse(\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e). In the present study, of a total of 1778 patients hospitalized with COVID-19, approximately 5% presented with bacterial/fungal coinfections. We has investigated the risk factors associated with bacterial/fungal infections and developed machine learning-based models with robust predictive performance. The algorithm showed that comorbidities (diabetes, neurological diseases), invasive procedures (central venous catheter, urinary catheter), the baseline inflammatory markers levels (IL-6\u0026thinsp;\u0026lt;\u0026thinsp;10 pg/ml, PCT\u0026thinsp;\u0026gt;\u0026thinsp;0.5 ng/ml) and creatinine\u0026thinsp;\u0026lt;\u0026thinsp;44 umol/L were associated with an increased risk of bacterial/fungal infection. Our models included variables easily obtained from electronic medical databases, which made it easier to identify high-risk inpatients. When the estimated coinfection risk is low, it is recommended to limit or use antibiotics cautiously, whereas high-risk estimates suggest enhancing surveillance or resource reallocation through additional patient care or enhanced disinfection, which could improve the efficiency of hospital infection surveillance(\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e). Early detection of high-risk patients is beneficial for preventing hospital infection outbreaks, antibiotic overuse, and microbial resistance.\u003c/p\u003e \u003cp\u003eDiabetes is related to various infections, especially skin, lower respiratory tract, and urinary tract infections(\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e). A review(\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e) suggested that diabetes and its comorbidity may lead to some infectious diseases due to metabolic disturbances. Similarly, Suheda Erener(\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e) summarized the clinical data on diabetes and COVID-19 and showed that exaggerated immune system inflammation and an excessive synthesis of cytokines may render patients with diabetes vulnerable to infectious diseases. IL-6 which has diverse biological activities is a key cytokine that can modulate homeostasis and inflammation(\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e). Previous reports(\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e, \u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e) have shown that an acute infection response induces rapid production of IL-6, and activates the host defense mechanism against infection through elevated acute-phase proteins and the immune response. In our study, low levels of IL-6 had significant predictive value for bacterial/fungal infections, where a baseline value of IL-6\u0026thinsp;\u0026lt;\u0026thinsp;10 pg/ml was associated with a 1.7-fold greater risk of infection than was an IL-6\u0026thinsp;\u0026gt;\u0026thinsp;10 pg/ml. However, exacerbation synthesis of cytokines, cytokine storm, can deteriorate the patient's clinical conditions(\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e). Future studies could explore cytokine levels and changes at different stages of bacterial/fungal infection among COVID-19 patients and their impact on prognosis.\u003c/p\u003e \u003cp\u003ePCT is a well-known biomarker of bacterial infection and has been proven to be involved in the early recognition of bacterial coinfection in patients with influenza pneumonia. However, the value of PCT in predicting bacterial coinfection in patients with COVID-19 has remained unknown, PCT is a biomarker of disease severity(\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e, \u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e). A study showed that PCT has a high negative predictive value for ruling out community-acquired bacterial coinfection, and a baseline PCT level\u0026thinsp;\u0026gt;\u0026thinsp;0.5 ng/ml is a predictor of ICU mortality(\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e). In our study, we found that PCT\u0026thinsp;\u0026gt;\u0026thinsp;0.5 ng/ml was associated with an increased risk of bacterial coinfection, which might indicate the severity of COVID-19 considering that severely ill patients may be more likely to be infected. A meta-analysis concluded that PCT has limited predictive value for coinfection, but lower PCT levels might indicated a decreased risk of coinfection(\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e). Several studies have noted that high PCT levels at admission are associated with severe outcomes in critically ill patients(\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e, \u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e). Nonetheless, PCT could be used as a helpful tool to guide antibiotic therapy for COVID-19(\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e). In line with the findings of previous studies(\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e, \u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e), multivariate logistic analysis indicated that central venous and urinary catheters are associated with increased infection risk. The most common infection source of catheters is intradermal and catheter interface contamination by organisms, which may come from the patient's skin or from healthcare workers\u0026rsquo; hands. Patients with catheters have severe disease and lower immunity, so it is harder to defend against bacterial invasion. In our study, these factors were inputted as strong predictors for model development which gained promising results for risk estimates.\u003c/p\u003e \u003cp\u003eDiscrimination is a traditional performance metric in model evaluation that uses the AUCROC to compare models. In our study, the AUCROCs of the two models exceeded 0.85, which indicated good accuracy. Few studies have drawn calibration curves to evaluate the matching degree between predicted and actual probabilities(\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e). Our calibration lines are close to the ideal lines with well-calibrated probabilities. The decision curves showed that these models had greater standard net benefits across all risk thresholds, which indicated that early management of high-risk patients could be beneficial according to our models(\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eRecent studies have initiated the prediction models to identify bacterial coinfections among CPVID-19 patients. A study(\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e) in Italy calculated a predictive risk score by assigning a point value according to the β coefficient to classify patients at risk of bacterial coinfection. This intuitive approach may be useful in diagnostic testing and antibiotic use for community-acquired infections. RAWSON T M et al.(\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e) have demonstrated that a support vector machine (SVM) with 21 blood test variables can accurately predict positive microbiological samples. However, antibiotic therapy or other interventions might influence daily blood test results, and our study avoided this problem because we included blood test results at admission.\u003c/p\u003e \u003cp\u003eOur study has several limitations. First, we may underestimate the prevalence of bacterial/fungal infections due to the retrospective study design. Generally, clinicians and IPCs diagnose and report healthcare-associated infection cases, and the number of cases detected partly relies on the extent of their efforts and the sensitivities of surveillance. Second, there was no external testing available to evaluate the transportability and generalizability of the prediction models. Future studies could externally validate and update the models in different settings to apply the models in clinical practice.\u003c/p\u003e"},{"header":"Conclusions","content":" \u003cp\u003eOur results indicate that the machine learning models achieved strong predictive ability and may be effective clinical decision support tools for bacterial/fungal infection surveillance and for guiding antibiotic administration. The GLM suggested that patients with an IL-6 concentration\u0026thinsp;\u0026lt;\u0026thinsp;10pg/ml are more vulnerable to developing a bacterial/fungal infection.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003e\u003cem\u003eEthics approval and consent to participate\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe study protocol was approved by the Ethics Committee of Nanjing Drum Tower Hospital, Affiliated Hospital of Medical School, Nanjing University (NO.2023-433-02). All participants provided written informed consent after completing the description of the study.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eConsent for publication\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eAvailability of data and materials\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe datasets used and/or analyzed during the current study are available from the corresponding author upon reasonable request.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eCompeting interests\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors declare that they have no competing interests.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eAuthor contributions\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eMW and WL prepared the materials and collected the data. MW analyzed data and wrote the first draft of the manuscript. HW helped to proofread the manuscript. PS supervised the study and made critical revisions to the manuscript. PS analyzed and interpreted patient data regarding risk factors and bacterial/fungal coinfection. All the authors contributed to the study conception and design and approved the submitted version.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eAcknowledgement\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eWe thank all the doctors, laboratory technicians, and project administrators who made contributions to the databases. We are grateful to Huixue Jia from Peking University First Hospital and Jinqi Wang from the Central Hospital of Wuhan for the helpful discussions and critical opinions.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eFunding\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study was supported by the Project of Chinese Hospital Reform and Development Institute, Nanjing University (NDYGN2023040), and the special fund project of Nanjing Drum Tower Hospital Clinical Research (2023-LCYJ-MS-35).\u0026nbsp;\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eNasir N, Rehman F, Omair SF. Risk factors for bacterial infections in patients with moderate to severe COVID-19: A case‐control study. J MED VIROL. 2021;93(7):4564\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCheng K, He M, Shu Q, Wu M, Chen C, Xue Y. Analysis of the Risk Factors for Nosocomial Bacterial Infection in Patients with COVID-19 in a Tertiary Hospital. Risk Manage Healthc Policy. 2020;13:2593\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLansbury L, Lim B, Baskaran V, Lim WS. Co-infections in people with COVID-19: a systematic review and meta-analysis. J Infect. 2020;81(2):266\u0026ndash;75.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMarkovskaya Y, Gavioli EM, Cusumano JA, Glatt AE. Coronavirus disease 2019 (COVID-19): Secondary bacterial infections and the impact on antimicrobial resistance during the COVID-19 pandemic. Antimicrob Stewardship Healthc Epidemiol. 2022;2(1).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKubin CJ, McConville TH, Dietz D, Zucker J, May M, Nelson B et al. Characterization of Bacterial and Fungal Infections in Hospitalized Patients With Coronavirus Disease 2019 and Factors Associated With Health Care-Associated Infections. OPEN FORUM INFECT DI. 2021 2021-06-01;8(6).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGajic I, Jovicevic M, Popadic V, Trudic A, Kabic J, Kekic D, et al. The emergence of multi-drug-resistant bacteria causing healthcare-associated infections in COVID-19 patients: a retrospective multi-centre study. J HOSP INFECT. 2023;137:1\u0026ndash;7.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSilva A DL, MLA C, CRME V, MBA L, TAPA N. B RBC, Fungal and bacterial coinfections increase mortality of severely ill COVID-19 patients. J HOSP INFECT. 2021.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGarcia-Vidal C, Sanjuan G, Moreno-Garc\u0026iacute;a E, Puerta-Alcalde P, Garcia-Pouton N, Chumbita M, et al. Incidence of co-infections and superinfections in hospitalized patients with COVID-19: a retrospective cohort study. CLIN MICROBIOL INFEC. 2021;27(1):83\u0026ndash;8.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRawson TM, Hernandez B, Wilson RC, Ming D, Herrero P, Ranganathan N et al. Supervised machine learning to support the diagnosis of bacterial infection in the context of COVID-19. JAC Antimicrob Resist. [Journal Article]. 2021 2021-03-01;3(1):b2.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVaughn VM, Gandhi TN, Petty LA, Patel PK, Prescott HC, Malani AN et al. Empiric Antibacterial Therapy and Community-onset Bacterial Coinfection in Patients Hospitalized With Coronavirus Disease 2019 (COVID-19): A Multi-hospital Cohort Study. CLIN INFECT DIS. 2021 2021-05-18;72(10):e533\u0026ndash;41.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGiannella M, Rinaldi M, Tesini G, Gallo M, Cipriani V, Vatamanu O, et al. Predictive model for bacterial co-infection in patients hospitalized for COVID-19: a multicenter observational cohort study. Infection. 2022;50(5):1243\u0026ndash;53.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNovacescu AN, Buzzi B, Bedreag O, Papurica M, Rogobete AF, Sandesc D et al. Bacterial and Fungal Superinfections in COVID-19 Patients Hospitalized in an Intensive Care Unit from Timișoara, Romania. INFECT DRUG RESIST. 2022 2022-01-01;15:7001\u0026ndash;14.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCheng K, He M, Shu Q, Wu M, Chen C, Xue Y. Analysis of the Risk Factors for Nosocomial Bacterial Infection in Patients with COVID-19 in a Tertiary Hospital. 2020;Vol. 13:2593\u0026ndash;9.\u0026lt;\\/bib\u0026gt;\u0026lt;\\/p\u0026gt;\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMoreno-Garc\u0026iacute;a E, Puerta-Alcalde P, Letona L, Meira F, Due\u0026ntilde;as G, Chumbita M,. Bacterial co-infection at hospital admission in patients with COVID-19. INT J INFECT DIS. 2022;118:197\u0026ndash;202.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMoreno-Torres V, de Mendoza C, de la Fuente S, S\u0026aacute;nchez E, Mart\u0026iacute;nez-Urbistondo M, Herr\u0026aacute;iz J,. Bacterial infections in patients hospitalized with COVID-19. INTERN EMERG MED. 2022;17(2):431\u0026ndash;8.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKumar G, Adams A, Hererra M, Rojas ER, Singh V, Sakhuja A,. Predictors and outcomes of healthcare-associated infections in COVID-19 patients.INT J INFECT DIS. 2021;104:287\u0026ndash;92.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGAO Jing*, CHEN Yong, WANG Pengfei, .Construction and validation of the prediction model for critical COVID-19 combined with bacterial or fungal infection.Infect Dis Info, 36, 3, June 30, 2023\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen PC, Liu Y, Peng L. How to develop machine learning models for healthcare. NAT MATER. 2019 2019-01-01;18(5):410\u0026ndash;4.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVan Calster B, Wynants L, Verbeek JFM, Verbakel JY, Christodoulou E, Vickers AJ,. Reporting and Interpreting Decision Curve Analysis: A Guide for Investigators.EUR UROL. 2018;74(6):796\u0026ndash;804.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAlnimr AM, Alshahrani MS, Alwarthan S, AlQahtani SY, Hassan AA, BuMurah NN,. Bacterial and Fungal Coinfection in Critically Ill COVID-19 Cases and Predictive Role of Procalcitonin During the First Wave at an Academic Health Center.J Epidemiol Glob Health. [Journal Article; Review]. 2022 2022-06-01;12(2):188\u0026ndash;95.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCho SY, Kim Z, Chung DR, Cho BH, Chung MJ, Kim JH,. Development of machine learning models for the surveillance of colon surgical site infections.The Journal of hospital infection. [Journal Article]. 2023 2023-04-22.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAkash M, Rehman K, Fiayyaz F, Sabir S, Khurshid M. Diabetes-associated infections: development of antimicrobial resistance and possible treatment strategies. ARCH MICROBIOL. [Journal Article; Review]. 2020 2020-07-01;202(5):953\u0026ndash;65.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eErener S. Diabetes, infection risk and COVID-19. MOL METAB. [Journal Article; Research Support, Non-U.S. Gov't; Review]. 2020 2020-09-01;39:101044.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKishimoto T, Kang S. IL-6 Revisited: From Rheumatoid Arthritis to CAR T Cell Therapy and COVID-19. ANNU REV IMMUNOL. [Journal Article; Research Support, Non-U.S. Gov't; Review]. 2022 2022-04-26;40:323\u0026thinsp;\u0026ndash;\u0026thinsp;48.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHeinrich PC, Castell JV, Andus T. Interleukin-6 and the acute phase response.BIOCHEM J. [Journal Article; Review]. 1990 1990-02-01;265(3):621\u0026ndash;36.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eArjmand B, Alavi-Moghadam S, Sarvari M, Rezaei-Tavirani M, Rezazadeh-Mafi A, Arjmand R,. Critical roles of cytokine storm and bacterial infection in patients with COVID-19: therapeutic potential of mesenchymal stem cells.INFLAMMOPHARMACOLOGY. [Journal Article; Review]. 2023 2023-02-01;31(1):171\u0026ndash;206.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHeer RS, Mandal AKJ, Szawarski P, Missouris CG. Procalcitonin is a biomarker for disease severity rather than bacterial co-infection in COVID-19.EUR J EMERG MED. 2022;29(4):315.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVazzana N, Dipaola F, Ognibene S. Procalcitonin and secondary bacterial infections in COVID-19: association with disease severity and outcomes. ACTA CLIN BELG. [Journal Article; Meta-Analysis]. 2022 2022-04-01;77(2):268\u0026ndash;72.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCarbonell R, Urgel\u0026eacute;s S, Salgado M, Rodr\u0026iacute;guez A, Reyes LF, Fuentes YV,. Negative predictive value of procalcitonin to rule out bacterial respiratory co-infection in critical covid-19 patients.J Infect. [Journal Article; Research Support, Non-U.S. Gov't]. 2022 2022-10-01;85(4):374\u0026ndash;81.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWei S, Wang L, Lin L, Liu X. Predictive values of procalcitonin for coinfections in patients with COVID-19: a systematic review and meta-analysis.VIROL J. [Journal Article; Meta-Analysis; Research Support, Non-U.S. Gov't; Review; Systematic Review]. 2023 2023-05-08;20(1):92.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLugito N. Is procalcitonin a part of human immunological response to SARS-CoV-2 infection or just a marker of bacterial coinfection? CURR RES TRANSL MED. [Letter]. 2021 2021-05-01;69(2):103289.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWolfisberg S, Gregoriano C, Schuetz P. Procalcitonin for individualizing antibiotic treatment: an update with a focus on COVID-19. Crit Rev Clin Lab Sci. [Journal Article; Review]. 2022 2022-01-01;59(1):54\u0026ndash;65.\u003c/span\u003e\u003c/li\u003e\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":"antimicrobial-resistance-and-infection-control","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"aric","sideBox":"Learn more about [Antimicrobial Resistance and Infection Control](http://aricjournal.biomedcentral.com/)","snPcode":"13756","submissionUrl":"https://submission.nature.com/new-submission/13756/3","title":"Antimicrobial Resistance \u0026 Infection Control","twitterHandle":"@ARICJournal","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"machine learning, predictive model, bacterial/fungal infection, healthcare-associated, nosocomial infection","lastPublishedDoi":"10.21203/rs.3.rs-3847614/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3847614/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eCOVID-19 and bacterial/fungal coinfections have posed significant challenges to human health. However, there is a lack of good tools for predicting coinfection risk to aid clinical work.\u003c/p\u003e\u003ch2\u003eObjective\u003c/h2\u003e \u003cp\u003eWe aimed to investigate the risk factors for bacterial/fungal coinfection among COVID-19 patients and to develop machine learning models to estimate the risk of coinfection.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eIn this retrospective cohort study, we enrolled adult inpatients confirmed with COVID-19 in a tertiary hospital between January 1 and July 31, 2023, in China and collected baseline information at admission. All the data were randomly divided into a training set and a testing set at a ratio of 7:3. We developed the generalized linear and random forest models for coinfections in the training set and assessed the performance of the models in the testing set. Decision curve analysis was performed to evaluate the clinical applicability.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eA total of 1244 patients were included in the training cohort with 62 healthcare-associated bacterial/fungal infections, while 534 were included in the testing cohort with 22 infections. We found that patients with comorbidities (diabetes, neurological disease) were at greater risk for coinfections than were those without comorbidities (OR\u0026thinsp;=\u0026thinsp;2.79, 95%CI\u0026thinsp;=\u0026thinsp;1.61\u0026ndash;4.86; OR\u0026thinsp;=\u0026thinsp;1.93, 95%CI\u0026thinsp;=\u0026thinsp;1.11\u0026ndash;3.35). An indwelling central venous catheter or urinary catheter was also associated with an increased risk (OR\u0026thinsp;=\u0026thinsp;2.53, 95%CI\u0026thinsp;=\u0026thinsp;1.39\u0026ndash;4.64; OR\u0026thinsp;=\u0026thinsp;2.28, 95%CI\u0026thinsp;=\u0026thinsp;1.24\u0026ndash;4.27) of coinfections. Patients with PCT\u0026thinsp;\u0026gt;\u0026thinsp;0.5 ng/ml were 2.03 times (95%CI\u0026thinsp;=\u0026thinsp;1.41\u0026ndash;3.82) more likely to be infected. Interestingly, the risk of coinfection was also greater in patients with an IL-6 concentration\u0026thinsp;\u0026lt;\u0026thinsp;10 pg/ml (OR\u0026thinsp;=\u0026thinsp;1.69, 95%CI\u0026thinsp;=\u0026thinsp;0.97\u0026ndash;2.94). A creatinine concentration\u0026thinsp;\u0026lt;\u0026thinsp;44 umol/L (OR\u0026thinsp;=\u0026thinsp;0.40, 95%CI\u0026thinsp;=\u0026thinsp;0.22\u0026ndash;0.71) was a protective factor. The generalized linear and random forest models demonstrated favorable receiver operating characteristic curves (ROC\u0026thinsp;=\u0026thinsp;0.87, 95%CI\u0026thinsp;=\u0026thinsp;0.80\u0026ndash;0.94; ROC\u0026thinsp;=\u0026thinsp;0.88, 95%CI\u0026thinsp;=\u0026thinsp;0.82\u0026ndash;0.93) with high accuracy, sensitivity and specificity of 0.86vs0.75, 0.82vs0.86, 0.87vs0.74, respectively. The corresponding calibration evaluation \u003cem\u003eP\u003c/em\u003e statistics were 0.883 and 0.769.\u003c/p\u003e\u003ch2\u003eConclusions\u003c/h2\u003e \u003cp\u003eOur machine learning models achieved strong predictive ability and may be effective clinical decision support tools for identifying COVID-19 patients at risk for bacterial/fungal coinfection and guiding antibiotic administration. The levels of cytokines, such as IL-6, may affect the status of bacterial/fungal coinfection.\u003c/p\u003e","manuscriptTitle":"Development and validation of machine learning-based models for predicting healthcare-associated bacterial/fungal infections among COVID-19 inpatients: a retrospective cohort study","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-01-11 18:24:09","doi":"10.21203/rs.3.rs-3847614/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-03-07T15:27:07+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-02-16T20:18:06+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"27d8ae95-b703-4639-8e69-0f924bf0969a_SNPRID","date":"2024-01-27T18:10:49+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"13af582e-f84f-49f3-9f8a-789da72eb466","date":"2024-01-27T17:24:04+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-01-24T03:33:08+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-01-11T07:26:54+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-01-10T06:34:45+00:00","index":"","fulltext":""},{"type":"submitted","content":"Antimicrobial Resistance \u0026 Infection Control","date":"2024-01-09T07:57:30+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"antimicrobial-resistance-and-infection-control","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"aric","sideBox":"Learn more about [Antimicrobial Resistance and Infection Control](http://aricjournal.biomedcentral.com/)","snPcode":"13756","submissionUrl":"https://submission.nature.com/new-submission/13756/3","title":"Antimicrobial Resistance \u0026 Infection Control","twitterHandle":"@ARICJournal","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"c1e554d2-8b7b-4e7d-8135-6efb62c535a2","owner":[],"postedDate":"January 11th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-04-14T19:49:05+00:00","versionOfRecord":{"articleIdentity":"rs-3847614","link":"https://doi.org/10.1186/s13756-024-01392-7","journal":{"identity":"antimicrobial-resistance-and-infection-control","isVorOnly":false,"title":"Antimicrobial Resistance \u0026 Infection Control"},"publishedOn":"2024-04-14 19:49:05","publishedOnDateReadable":"April 14th, 2024"},"versionCreatedAt":"2024-01-11 18:24:09","video":"","vorDoi":"10.1186/s13756-024-01392-7","vorDoiUrl":"https://doi.org/10.1186/s13756-024-01392-7","workflowStages":[]},"version":"v1","identity":"rs-3847614","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3847614","identity":"rs-3847614","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}