Impact analysis and predictive modeling in emergency care： Evaluating the effects of immediately post-COVID-19 lockdown at a top Chinese teaching hospital

Impact analysis and predictive modeling in emergency care： Evaluating the effects of immediately post-COVID-19 lockdown at a top Chinese teaching hospital | 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 Impact analysis and predictive modeling in emergency care： Evaluating the effects of immediately post-COVID-19 lockdown at a top Chinese teaching hospital Yuanyuan Pei, Xi Wang, Lingjie Cao, Dilu Li, Liping Guo, Fengtao Yang, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4326543/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Background Coronavirus disease of 2019 (COVID-19) has caused a global pandemic. Emergency department (ED) suffered a significant impact due to COVID-19 spread after policy adjustments at the end of 2022 in China. Methods This study analyzed the impact of post-COVID-19 lock-down on ED visits and critically ill patients at Peking University People's Hospital from December 2022 to January 2023. Machine learning was employed to identify key predictors of mortality in critically ill ED patients. A Graphical User Interface (GUI) was developed to estimate the prognostic predictors. Results We have observed a significant rise in ED visits and admissions of critical patient, particularly with COVID-19 pneumonia. A total of 25413 patients visited ED, of who 631 patients were critically ill. Our analysis of 581 critical patients revealed distinct clinical and demographic characteristics like hypertension and diabetes, with a notable prevalence of complications such as acute respiratory distress syndrome, acute kidney injury and respiratory failure. We further studied the variables with high contribution to model prediction to observe the characteristic differences between the variables in the non-survival group and the survival group. Age, hypoxic state and ventilator support, white blood cell, platelets, and coagulation indicators were identified as key risk factors for mortality using a Random Forest model. The study's predictive model demonstrated high accuracy, with its area under the receiver-operator curve as 0·8385, which incorporated into a user-friendly GUI for clinical application and could enhance the management of critical COVID-19 cases in emergency settings. Conclusion The pandemic spread rapidly in China after the quarantine was lifted. The predictive score and GUI for estimating prognostic risk factors in ED critical patients can be used to aid in the proper treatment and optimizing medical resources. COVID-19 Post-COVID-19 lockdown Emergency department Machine learning Prognostic predictors Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Key Points Question: For a long period, China implemented extensive lockdowns for COVID-19, insights into the post COVID-19-lockdown era remain sparse. Findings: In this study of 25413 patients who visited ED, of whom 631 patients were critically ill. To identify key predictors of mortality in critical patients, machine learning was utilized. The study developed a predictive model with a graphical user interface (GUI) that could accurately predict the prognosis of critical patients. Meaning: Our findings highlight the significant impact of the post COVID-19-lockdown period on ED. The development of a predictive model is consequential for enhancing decisions and medical resources distribution in ED care. Introduction Coronavirus disease of 2019 (COVID-19) is a disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), has resulted in a global pandemic. 1,2 Over 760 million cases and 6·9 million deaths have been recorded worldwide, but the actual number is thought to be higher. 1,2 The initial outbreak in December 2019 consisted of 27 patients with pneumonia in Wuhan, Hubei Province, China. 3 Then the virus spread around the world with great rapidity and was immediately declared as a pandemic. 1–3 The pandemic necessitated the implementation of stringent lockdown measures worldwide, with China being one of the first countries to impose such restrictions. 4–6 Neverthless, as the virus continues to mutate, especially the Delta and Omicron variants, have resulted in a series of local outburst in China. 4,7–9 Accordingly, China liberalized its control of COVID-19 at the end of 2022. The call off of the lockdown marked a critical transition in the management of the pandemic. Healthcare systems, particularly emergency services, faced the dual challenge of managing a potential resurgence of COVID-19 cases and addressing the backlog of non-COVID medical needs that had accumulated during the lockdown. This study examines the aftermath of reducing the COVID-19 lockdown in the emergency department (ED) of a top teaching hospital in China, focusing on the impact on patient care and outcomes, and provides a unique opportunity to study the dynamics of healthcare delivery during a post-lockdown period. Meanwhile, it also offers a comprehensive view of the challenges and adaptations in a high-volume ED environment. By predictive analytics, this study aims to assess the impact of post-COVID-19 lockdown on patient inflow, disease spectrum, complications, laboratory indicators, and prognostic factor, as well as COVID-19 pneumonia. This approach is especially useful in emergency care, where timely and efficient response is essential. Recently, progress in artificial intelligence (AI) technology for disease screening indicate potential as computer-aided diagnosis and prediction tools. 10–14 AI might represent a novel and useful technology for the management of critical patients to quickly predict mortality, which helps to risk stratify patients and provide targeted treatment according to different groups. A robust predictive model is developed in this study to help in planning and optimizing emergency care services in the face of healthcare challenges after COVID-19 lockdown. Therefore, this study provides a vital analysis of the effects of lifting the COVID-19 lockdown on emergency healthcare services, while exploring how predictive analytics can enhance the response to future healthcare crises. Methods Study population From December 2022 to January 2023, all patients admitted to ER, Peking University People’s Hospital in China were enrolled in this observational study. Procedures Firstly, we observed the dynamic change of numbers of daily emergency consulting room visits, who were patients with mild and moderate symptoms. Then we divided the patients into four subgroups to analyze the changes in the number of visits, including internal emergencies, surgical emergencies, gynecological emergencies, and other emergencies (otolaryngology and ophthalmology), respectively. Next, we surveyed the total number of critically ill patients admitted to the emergency resuscitation room every day, and analyze the spectrum of underlying diseases, including COVID-19 severe pneumonia, severe pneumonia not caused by COVID-19, cardiovascular emergencies (acute myocardial infarction and acute heart failure), gastrointestinal system emergencies (gastrointestinal bleeding, severe pancreatitis, cirrhosis), central nervous system emergencies (cerebral hemorrhage, subarachnoid hemorrhage and acute cerebral infarction), hematological emergencies (acute leukemia, hemophagocytic syndrome, severe anemia, and so on), endocrine system emergencies (hyperglycemic crisis, hypoglycemic coma), sepsis, sudden death, surgical emergencies, rheumatological emergencies and other causes. Furthermore, we collected baseline characteristics data from all critical patients admitted to the emergency resuscitation room. Demographic data including age, sex, comorbidities (hypertension, diabetes mellitus, coronary heart disease, heart failure, asthma, chronic obstructive pulmonary disease, interstitial lung disease, chronic kidney disease, cerebral diseases, hematological diseases, rheumatic diseases and immunosuppression state), time from onset to admission (day) and initial vital signs were collected. Meanwhile, we assessed complications including acute respiratory distress syndrome (ARDS), respiratory failure, acute myocardial injury, acute liver injury (ALI), acute kidney injury (AKI), hyperfunction of the fibrinolysis and disseminated intravascular coagulation (DIC). In addition, laboratory indicators included levels of white blood cell, hemoglobin, and platelet counts, C-reactive protein (CRP), procalcitonin (PCT), interleukin-6 (IL-6), lactate, hypersensitive troponin I (hsTNI), brain natriuretic peptide(BNP), aspartate transaminase (AST), alanine transaminase (ALT), total bilirubin, direct bilirubin, albumin, blood urea nitrogen(BUN), creatinine, estimate glomerular filtration rate (eGFR), serum triglyceride, prothrombin time (PT), activated partial thromboplastin time (APTT), fibrinogen, fibrinogen degradation products (FDP), and D-dimer levels. Drug and supportive treatment include the use of antibiotics, glucocorticoids, baricitinib, tocilizumab, gamma globulin, oxygen therapy, noninvasive ventilation, mechanical ventilation and extracorporeal membrane oxygenation (ECMO) were recorded accordingly. Each record was checked independently by 2 clinicians. Definitions COVID-19 diagnoses were confirmed by positive antigen testing and/or high throughput sequencing or real-time reverse-transcription polymerase-chain-reaction (RT-PCR) assay or for nasal and pharyngeal swab specimens, with typical imaging manifestations by chest CT. 15,16 ARDS was diagnosed according to the Berlin definition, including acute onset (within 7 days of new or worsening respiratory symptoms), bilateral radiographical opacities that are not fully explained by effusion, atelectasis or masses, arterial hypoxemia, identified risk factor for ARDS and not exclusively due to cardiac causes. 17 Respiratory failure is defined as arterial oxygen partial pressure < 60mmHg in the non-oxygenated state. Transaminase ≥ 3 fold the normal upper limit is defined as acute liver injury (ALI). Myocardial injury was diagnosed according to the elevation of cardiac hypersensitive troponin I. Acute kidney injury (AKI) is characterized by an increase in serum creatinine of 0·3 mg/dl within 48 h, an elevation on to 1·5 fold the baseline level within the first 7 days, or a decline in urine output to not more than 0·5mL/kg per hour for at least 6 hours in accordance with 2012 KDIGO definition. 18 CKD was defined according to the definition of the National Kidney Foundation as kidney damage or eGFR of less than 60 ml/min per 1·73 m 2 for at least 3 months. 19 Hyperfunction of the fibrinolysis system was confirmed by the obvious increase of fibrinogen, FDP and D-dimers. DIC was diagnosed according to the International Society on Thrombosis and Haemostasis scientific standardization subcommittee, including elevated levels of fibrin-related markers such as fibrin/FDP or D-dimers, decreased platelet counts, prolonged prothrombin time, and decreased fibrinogen levels. 20 Data processing In this retrospective investigation, we focused on a cohort of 631patients, encompassing a total of 99 variables, including both laboratory and clinical data. All variables were tested for normal distribution using the Kolmogorov-Smirnov test. All descriptive statistics are summarized and shown as mean ± standard deviation or median (25–75%). Patients with integral clinical data stands at 581, providing the basis for descriptive statistical analysis. A stringent data cleansing protocol was applied before finalizing the dataset for the machine learning model. Where a feature had more than 50% of missing values or when more than 50% of a patient's features were missing, we will proceed to remove variables or patients, resulting in a refined cohort of 550 cases. In the realm of the existing dataset, a methodological approach of interpolation has been systematically employed to impute the precise data points. For numerical features, we employed Bayesian linear regression, while binary variables were imputed using logistic regression. As a result, we obtained a dataset consisting of 82 variables and 550 patient records for model development and validation. To assess the model's performance, we randomly allocated 20% of the data for testing and verification purposes. The data imputation procedures were carried out using the R programming language in this study. Mosdel development and feature selection We used the random forest (RF), support vector machine (SVM), linear discriminant analysis (LDA), Gaussian Naive Bayes (GaussianNB), logistic regression (LR), and Multilayer Perceptron (MLP) for prediction. The model's accuracy was assessed using the area under the receiver-operator curve (AUC). We utilized AUC to compare the accuracy of these six machine learning models and selected the optimal model for identifying the top 15 variables contributing most significantly to the prediction. To reduce the model's feature space dimensionality, we exclusively employed these 15 parameters with the highest predictive values to train the model and design the software. Additionally, we conducted further comparisons and validation of machine learning methods, documenting their AUC, accuracy, precision, F1-score, and specificity. All machine learning algorithms were implemented using the Python programming language in this study. The construction of the Graphical User Interface (GUI) The Graphical User Interface (GUI) construction involved utilizing Python's PyQt5 library for user interaction. This interface integrated input fields and buttons to receive user data. The data underwent processing and was inputted into a pre-trained classifier. The resultant predictions, probability scores, and labels were then displayed for user interpretation, serving to enhance accessibility for managing critical COVID-19 cases in emergency settings. Results Overview of patient demographics and clinical characteristics Overall, a total of 24792 patients were enrolled in the emergency consulting room in two months between December 6, 2022 and January 31, 2023. Meanwhile, 631 critically ill patients admitted to the emergency resuscitation room during this period, and in-hospital mortality was 32·2% (203/631). As shown in Fig. 1 , We further analyzed the underlying disease composition of all critically ill patients. Among all causes, the proportion of COVID-19 was 59·59% (n = 376), which is predominant, acute cardiovascular diseases was 7·61% (n = 48), gastrointestinal emergencies was 5·71% (n = 36), pneumonia not caused by COVID-19 was 5·23% (n = 33), central nervous system emergencies was 4·91% (n = 31), sudden death was 3·01% (n = 19), hematological system emergencies was 2·69% (n = 17), endocrine system emergencies was 1·74% (n = 11), surgical emergencies was 1·74% (n = 11), sepsis was 1·11% (n = 7), rheumatic immune system emergency was 0·63% (n = 4), and other causes 6·02% (n = 38), respectively. Dynamic changes in daily emergency room visits post COVID-19 lockdown As displayed in Fig. 2 , the total number of daily visits to the emergency consulting room showed a progressive elevation during the whole December post COVID-19 lockdown. The number of daily consultations rose from 270 at the beginning to over 600 progressively, peaked at 668 on December 30, and then showed a gradual decline, eventually returning to the initial baseline levels. In contrast, January experienced a reduction in medical emergencies but observed a gradual increase in surgical emergency. The frequency of gynecological and other types of emergencies remained consistent during this period. Disease composition in critically ill patients Figure 3 illustrates a comparison between the trends in emergency critically ill patient admissions and the trends in consultations following the lockdown. The daily numbers of critical patients admitted to ED were less than 10 cases at the beginning (from December 6 to December 10), and then gradually went up, reaching a peak of 29 cases on January 2. After reaching the peak, it fluctuated down and returned to the initial level by the end of January. Among them, the daily numbers of critically ill patients are significantly correlated with the daily numbers of patients with pneumonia. In terms of underlying disease distribution, COVID-19 pneumonia patients accounted for the largest proportion of the whole critically ill patients, up to 59·6%. Meanwhile, the proportion of other common critical diseases in the ED, such as cardiovascular emergencies, gastrointestinal emergencies and central nervous system emergencies, is all below 10% respectively, which has been indicated in Fig. 1 . Profile of critically ill patients In the cohort, we collected data from all 631 critical patients. After excluding patients with excessive incomplete data, 581 patients were finally enrolled. Overall, the mean (SD) age of patients in this cohort was 80 (68, 87) years, 346 patients (59·6%) were men and 376 patients (64·7%) had severe COVID-19 pneumonia. In terms of coexisting condition, the proportion of hypertension, diabetes, coronary heart disease, cerebral diseases, CKD, heart failure, hematological diseases was 36·1% (210 patients), 40·0% (231 patients), 30·0% (173 patients), 28·6% (165 patients), 20·0% (116 patients), 12·8% (74 patients), 12·6% (73 patients), respectively. About complications, the incidence of ARDS, respiratory failure, AKI, acute myocardial injury, ALI, fibrinolytic hyperfunction, DIC and acute confusion was 28·8% (109 patients), 54·4% (252 patients), 34·5% (178 patients), 38·0% (189 patients), 24·6% (130 patients), 18·4% (96 patients), 12·9% (67 patients) and 23% (120 patients) accordingly. These baseline characteristics were shown in Table 1 . Table 1 Baseline characteristics of the patients in different outcomes groups Variables Total (n = 581) Remission group (n = 378) Death group (n = 203) P value Demographic data Age(years) 80(68,87) 77(64, 86) 82(73,88) 0.000 Male (%) 346(59.6) 211(55.8) 135(66.5) 0.013 COVID-19 pneumonia (%) 376(64.7) 211(55.8) 165(81.3) 0.024 Time from onset to admission (day) 5( 2 , 10 ) 4( 2 , 10 ) 5( 2 , 7 ) 0.419 Length of hospitliztion (day) 8( 2 , 17 ) 10( 2 , 20 ) 4( 1 , 13 ) 0.000 Comorbidities (%) Hypertension 210(36.1) 231(61.4) 137(67.8) 0.147 Diabetes 231(40.0) 152(40.4) 79(39.3) 0.859 Coronary heart disease 173(30.0) 107(28.5) 66(32.8) 0.295 Heart failure 74(12.8) 50(13.3) 24(11.9) 0.696 Cerebral diseases 165(28.6) 101(26.9) 64(31.8) 0.210 COPD 28(4.8) 21(5.6) 7(3.5) 0.314 Asthma 21(3.6) 12(3.2) 9(4.5) 0.485 Interstitial lung disease 25(4.3) 14(3.7) 11(5.5) 0.390 CKD 116(20.0) 67(17.7) 49(24.4) 0.064 Hematological diseases 73(12.6) 56(14.8) 17(8.5) 0.035 Rheumatic diseases 38(6.5) 26(6.9) 12(5.9) 0.727 Immunosuppression state 57(9.8) 37(9.8) 20(10.0) 1.000 Vital signs SBP (mmHg) 137(118,156) 138(118,156) 134(119,160) 0.841 DBP (mmHg) 75(65,87) 75(65,87) 74(65,87) 0.536 SpO2 (%) 88(80,94) 90(81,95) 86(75,92) 0.002 Tmax (℃) 38.5(37.7,39.0) 38.2(37.9,39.0) 38.5(37.6,39.0) 0.792 Complications (%) ARDS 109(28.8) 68(28.6) 41(29.1) 0.907 Respiratory failure 252(54.4) 149(51.6) 103(59.2) 0.123 AKI 178(34.5) 109(32.9) 69(37.3) 0.335 Acute myocardial injury 189(38.0) 113(35.3) 76(42.7) 0.063 ALI 130(24.6) 83(24.2) 47(25.3) 0.833 Fibrinolytic hyperfunction 96(18.4) 55(16.4) 41(22.2) 0.066 DIC 67(12.9) 37(11.0) 30(16.2) 0.062 Acute confusion 120( 23 ) 78(22.9) 42(23.2) 1.000 Furthermore, all critical emergencies were divided into the discharge group and in-hospital death group for univariate analysis. The results indicated that in-hospital death group were older, with more male and more percentage of COVID-19 pneumonia. Meanwhile, the death group tended to have lower SpO2 at admission, decreased WBC levels, as well as elevated CRP, IL-6, BUN, FDP, D-dimer and Lac levels. In terms of treatments, the death group had more proportion of oxygen therapy, noninvasive and mechanical ventilation. In addition, we found that although there was no statistical difference in complications such as acute myocardial injury, fibrinolytic hyperfunction and DIC between the groups, their incidence was still obviously increased in the death group, with P values from 0·062 to 0·066. Laboratory findings and treatments were presented in Tables 2 and 3 . Table 2 Laboratory characteristics of the patients in different outcomes groups Variables Total (n = 581) Remission group (n = 378) Death group (n = 203) P value Peak WBC (*10 9 /L) 10.5(7.7, 15.5) 10.6(7.3,15.3) 10.5(8.2,15.6) 0.558 Nadiral WBC(*10 9 /L) 6.4(4.5, 9.0) 6.2(4.1,8.8) 6.7(5.0,9.7) 0.010 Hemoglobin(g/L) 108(86, 126) 108(86, 126) 112(88, 127) 0.130 Platelets(*10 9 /L) 181(126, 249) 181(126, 249) 175(118,226) 0.304 CRP (mg/L) 75.8(25.0, 140.1) 62.9(15.8,130.6) 91.1(39.2, 152.4) 0.001 PCT (ng/ml) 0.39(0.122, 1.67) 0.35(0.12, 1.78) 0.42(0.12, 1.53) 0.976 AST (U/L) 38(24,71) 37(22, 70) 39(27, 77) 0.358 ALT (U/L) 27(15,49) 26(15, 53) 27(16, 45) 0.647 Tbil (mmol/L) 12.4(8.4,19.8) 12.4(8.4,19.8) 12.8(8.4, 20.4) 0.350 Dbil (mmol/L) 5.9(3.7,9.2) 5.8(3.7, 8,8) 6.0(3.7,10.7) 0.456 Triglyceride (mmol/L) 1.49(1.09, 2.07) 1.50(1.08, 2.05) 1.45(1.10, 2.07) 0.997 Albumin (g/L) 30.7(27.0,36.1) 30.8(26.7,36.2) 30.7(27.4, 36.0) 0.639 BUN (mmol/L) 11.8(7.3, 22.3) 11.0(6.9, 21.5) 13.9(8.3, 23.6) 0.020 SCr (µmol/L) 106(75, 195) 106(75, 195) 112(80,221) 0.087 eGFR (ml/min*1.73m 2 ) 53.04(24.91,80.76) 56.24(26.98, 81.94) 48.59(21.53, 78.49) 0.101 hsTNI 46.2(13.3,254.1) 43.4(12.1, 299.2) 55.6(15.2,222.8) 0.871 BNP 276(114,824) 256(102, 868) 181(157, 769) 0.355 Peak FIB (mg/dl) 441(361,522) 432(357, 514) 459(378,530) 0.071 Nadiral FIB (mg/dl) 341(249, 432) 336(253,420) 367(243,465) 0.160 Peak PT (s) 12.7(11.5,14.6) 12.7(11.6,15.0) 12.7(11.4,14.1) 0.349 Peak APTT (s) 31.4(28.7, 35.6) 31.4(28.7, 35.5) 31.6(28.7, 36.0) 0.906 Peak D-dimer (ng/ml) 1129(514,3723) 1065(473, 3353) 1713(553,5629) 0.022 Peak FDP (ug/ml) 8.1(3.9,27.3) 7.4(3.5, 21.4) 11.4(4.6, 41.7) 0.005 Lac (mmol/L) 2.2(1.3,3.9) 2.1(1.3, 3.2) 2.7(1.5,5.3) 0.028 Ferritin (ng/ml) 796(430, 1306) 659(324, 1337) 870(464, 1173) 0.318 IL-6 (pg/ml) 51.8(19.4, 180) 41.9(13.3, 118) 92.6(39.3, 322) 0.003 Table 3 Treatments in the patients of different outcome groups Treatments (%) Total (n = 581) Discharge group (n = 378) Death group (n = 203) P value Carbapenems 312(59.2) 197(58.5) 115(60.5) 0.712 Penicillin 98(18.6) 24(40.0) 52(51.0) 0.195 Cephalosporin 116(22.1) 75(22.3) 41(21.7) 0.913 Quinolone 41(21.7) 24(7.1) 17(9.0) 0.498 Aminoglycosides 98(18.6) 66(19.5) 32(16.9) 0.486 Tetracycline 14(2.7) 11(3.3) 3(1.6) 0.398 Fungal antibiotics 41(7.8) 24(7.1) 17(9.0) 0.498 Baritinib 13(2.5) 7(2.1) 6(3.2) 0.560 Tocilizumab 4(0.8) 2(0.6) 2(1.1) 0.621 Immunoglobulin 45(8.6) 30(8.9) 15(7.9) 0.748 Glucocorticoids 197(37.5) 118(35.0) 79(41.8) 0.133 Oxygen therapy 477(82.1) 292(77.2) 185(91.1) 0.000 Mechanical ventilation 55(9.5) 9(2.4) 46(22.9) 0.000 Noninvasive ventilation 140(24.2) 55(14.6) 85(42.3) 0.000 Resource utilization and hospital capacity During the post-COVID-19 lockdown period, there was a notable fluctuation in bed occupancy rates within the ED and across the hospital. The data indicates a significant increase in bed utilization, rising from 85 ~ 92% in the pre-lockdown phase to 100% post-lockdown. The distribution of resources, particularly ventilators and intensive care unit (ICU) beds, was significantly impacted. The demand for ventilators increases from 50–75–100% of available units, underscoring the severity of respiratory complications in COVID-19 cases. In response to these demands, the hospital re-allocated resources, converting general wards into COVID-19 units and increasing the number of beds in the ICU by 200%. These adjustments were critical in managing the heightened patient load while ensuring care for both COVID-19 and non-COVID-19 emergencies. The post-lockdown period necessitated significant adjustments in staffing within the ED. The staffing in the ED was increased by 250%, with a notable emphasis on recruiting internal specialists in infectious diseases, pulmonology, and critical care. These adaptations demonstrate the significance of healthcare systems that are both adaptable and responsive in the face of pandemics and large-scale public health emergencies. Development and evaluation of the predictive model In this study, we developed six machine learning models as described in the Methods section, and assessed their performance using scores from an independent test set based on AUC, Accuracy, Precision, F1-score, and Specificity Table 4 : Machine learning performance, which is a comparison of Model Performance Metrics: Area Under the Curve (AUC), Accuracy, Precision, F1-Score, and Specificity for Random Forest (RF), Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), Logistic Regression (LR), Gaussian Naive Bayes (GaussianNB), and Multilayer Perceptron (MLP). The Random Forest algorithm demonstrated as the the highest AUC score among the models (Figure. 4, a and b). In the selection of risk factors, we utilized the Gini coefficient from Random Forest as the criterion which in Random Forests gauges each feature's impact on prediction accuracy, amalgamating insights from multiple trees. Its use ensures reliability by mitigating overfitting risks and captures complex variable interactions, providing crucial insights for clinical predictions. After the model training, top 15 variables have been selected as significant predictors of critical illness, including mechanical ventilation, age, SPO2, WBC nadir, CRP peak, non-invasive ventilation, SBP, APTT peak, WBC peak, DBP, Direct bilirubin peak, PT peak, FIB nadir, FIB peak, and PLT nadir were determined as risk factors for patient mortality (Figure. 5). It is worth noting that COVID-19 was not selected as one of the top 15 fatal factors. Table 4 Machine learning performance RandomForest Lda SVM LR GaussianNB MLP AUC 0.8385 0.7585 0.7593 0.7259 0.7463 0.7092 Accuracy 0.7545 0.6818 0.6909 0.7091 0.609 0.6727 Precision 0.7519 0.6643 0.6758 0.6959 0.7047 0.6560 F1-score 0.7359 0.6545 0.6667 0.6848 0.6119 0.6586 Specificity 0.9167 0.8732 0.8732 0.8889 0.4930 0.8194 Model accuracy and clinical application After identifying the 15 risk factors, we refined the model to avoid redundancy, we focusing on the key indicators for the prediction of mortality. The final performance of the model demonstrated that the Random Forest algorithm maintained the highest-performing model with an AUC of 0·8385. Finally, to translate these analytical advancements into practical clinical tools, we developed a user-friendly Graphical User Interface (GUI). This GUI embodies the essence of our predictive algorithms, offering a streamlined and accessible interface for real-time application in clinical settings, particularly for managing critical cases of COVID-19 in emergency departments (Figure. 6). It provides clinicians with an efficient, intuitive tool to aid in decision-making processes. The software, designed for local use, is built upon the sklearn library in Python and features a PyQt5 graphical interface, ensuring both reliability and ease of use in a demanding healthcare environment. Discussion According to our findings, there has been a significant increase in emergency department (ED) visits, especially for patients with COVID-19 pneumonia who are critically ill. The entire period lasted about 2 months, a total of 25423 patients visited the ED, including 631 critically ill patients. Initially, there was a significant increase in both general and critical emergencies, with general cases mainly involving internal ailments and critical cases mainly involving severe COVID-19 pneumonia. The peak lasted for approximately 20 days, and daily consultations reached a high of 668 on December 30 and remained above 500 for 14 days. As internal emergencies decreased and surgical cases rose, visit numbers returned to normal by late January 2023. This surge underscores the ongoing challenges in healthcare systems in managing pandemic-related cases alongside routine emergencies. In consistent with the health and medical care situation faced by other countries and regions, ED has faced a variety of serious stiff issues during the whole break period, including the shortage of medical resources, the infection of the medical health team, overloaded and sustained high intensity work state, effort-reward imbalance. 22,23 As previously mentioned, bed occupancy, oxygen and ventilators shortage are both highly intense in the ED. Under this broad environment of epidemic, our hospital has taken a series of immediate measures to alleviate the scarce resources, including bed utilization, ICU bed expansion, establishment and conversion of COVID-19 units, the assignment and supportment of ED staff. These adjustments have revealed the adaptation and responsibility of healthcare systems is crucial when facing a major public health crisis. In addition to the overall macroscopical controlment, it is also vital to seek a reasonable and reliable rapid diagnosis and prediction tool, for the optimized diagnosis and therapies of the total critical patients. Computational assistance has indicated its advantage to ED care providers, who under high tension and exhaustion might lead to a decline in the accuracy of clinical judgment, resulting in increased mortality rates. 24,25 Beyond the general benefits of data-driven decision-making, AI could help clinical professionals determine who needs a critical level of care more precisely. In this study, we employed a novel machine-learning method using routine clinical and laboratory data to predict mortality in critically ill patients in the Emergency Department during an epidemic outbreak. This is the first study of its kind to develop a mortality prediction risk model for Chinese ED patients, predominantly affected by COVID-19. Meanwhile, the six machine learning models were trained and tested to find the optimal model and used the gini coefficient to screen risk factors to increase the interpretability of the model. Furthermore, we developed and validated a software-based risk calculator t perform risk scoring and predict the development of critical illness among ED patients. The performance of this risk score was satisfactory with accuracy based on a reliable AUROC as 0·8385 and 15 variables were included, which has the capability to accurately discern patients' likelihood of survival or mortality. The predictive model developed in this study demonstrates high accuracy, suggesting its potential as a valuable asset in emergency care protocols. It is found that all critical emergencies were elder people predominantly, and age is a risk factor for poor prognosis, which is consistent with previous studies. 24,26–28 Patients with lower SpO2 and treated with noninvasive ventilation and mechanical ventilation tended to have a higher mortality for the severe respiratory dysfunction. 24,28,29 Elevated direct bilirubin has also been found to be associated with poor studies in several studies, which is consistent with our study. 26 Cytokine storms are well-known to play an important role in the pathophysiological process of COVID-19. 27,30,31 Persistent high inflammatory state and immune dysfunction have been found to be associated with increased mortality in numerous studies. 30–33 The proinflammatory state can be manifested as a significant elevation in WBC, ferritin, CRP, IL-6, IL-1 and other inflammatory cytokine. On the other side, the immune dysfunction is accompanied by a decrease in WBC and lymphocyte counts, which leads to an increase in secondary and opportunistic infections. 33,34 This phenomenon has also been observed in this study. The disturbance of coagulation system is a common and critical complication in COVID-19 patients. 35–37 All coagulation and fibrinolysis parameters can be affected by COVID-19, including APTT, PT, fibrinogen, FDP, D-dimer and platelet count, which is called COVID-19 induced coagulopathy in the early stage, and with the progression of the disease, it can develop into DIC, resulting in a substantial morbidity and mortality. 35–37 In this study, it could be observed that coagulation dysfunction including fibrinolytic hyperfunction and DIC has a higher occurrence in the death group. Accordingly, prolonged APTT and PT, alteration of fibrinogen and decreased platelets levels are both correlated with poor in-hospital prognosis through machine learning. A key innovation of our study is the application of machine learning techniques to identify mortality predictors in COVID-19 patients. This approach not only contributes to the existing body of knowledge but also offers a practical tool for healthcare practitioners in emergency settings. Based on the above variables we found, a user-friendly GUI is established, which requires further clinical validation. The GUI developed as part of this study serves as a user-friendly platform for rapidly assessing patient risk, aiding in timely and informed decision-making. The current development of wearable systems makes continuous and predictive monitoring possible. However, in a clinical setting, the monitoring of patients still relies on intermittent observations of vital signs combined with the use of EWS. The objective of this study was to develop an approach for real-time outcome prediction based on continuous vital signs monitoring and advanced machine learning techniques. The potential limitations of this study merit consideration. First, the data is confined to a single institution and a specific post-lockdown period, which may affect the generalizability of the findings. Future research should focus on replicated this study in various locations and for extended periods to validate and enhance the predictive model. Second, the omission of certain prognostic indicators like IL-6 and Lac due to excessive missing data may impact the study's comprehensiveness. Third, the sample size for both constructing and validating the risk score is small, and the data being exclusively from China could limit its applicability globally. The model's reliability and applicability across diverse populations requires further validation studies, especially from outside China. In summary, this study provides valuable insights into the increased emergency department visits at a top teaching hospital in China following the COVID-19 lockdown. The importance of machine learning in healthcare is underlined, especially through the creation of a predictive model with a graphical user interface. By using initial hospital admission data, this innovation aids in accurately assessing the risk of critically ill patients. These advancements are essential for improving treatment decisions and efficiently allocating medical resources in emergency care, which can help solve ongoing healthcare challenges. Declarations Funding This study was funded by the Key Technologies Research and Development Program (grant numbers 2022YFE0131700, 2022YFC3602000) and the National Natural Science Foundation of China (grant numbers 82071813, 82271835). These funding sources supported all phases of this research, including design, collection, analysis, and interpretation of data. Author information Authors and Affiliations 1. Department of Emergency, Peking University People’s Hospital, Beijing, China 2. School of biomedical sciences and engineering, South China University of Technology, Guangzhou, China 3. Department of Rheumatology and Immunology, Peking University People's Hospital, Beijing, China Contributions Yuanyuan Pei, Xi Wang, Jing He and Jihong Zhu contributed to the concept and design of this work. Lingjie Cao, Dilu Li, Liping Guo, Fengtao Yang and Wenfeng Huang participated in clinical data entry. Xi Wang was responsible for the statistical data analysis and machine learning. Hao Li and Yuanyuan Pei provides guidance on clinical data analysis methods. Yuanyuan Pei and Xi Wang was responsible for the article writing. All authors have read and approved the final manuscript and agree to be accountable for all aspects of the work. Corresponding author Correspondence to ; Jing Heand Jihong Zhu Ethics Approval and Consent to Participate All procedures performed in this study involving human participants were in accordance with the ethical standards of the institutional research committee and with the 1964 Helsinki declaration and its later amendments. This study was approved by the hospital ethics committee (reference No. 2023PHB217-001). Informed Consent Informed consent was obtained from all patients or their family members included in the study. Consent for Publication N/A. Availability of data and materials The datasets used or analyzed in this study are available from the corresponding author upon reasonable request. Declaration of interests The authors declare that they have no conflicts of interest. References World Health Organization. Available from: https://www.who.int/news-room/fact-sheets/detail/ coronavirus-disease- (covid-19). [Accessed 30th January 2024] Crook H, Raza S, Nowell J, Young M, Edison P. Long covid-mechanisms, risk factors, and management. BMJ . 2021; 374 :n1648. https://doi.org/10.1136/bmj.n1648 Chen T, Wu D, Chen H, et al. Clinical characteristics of 113 deceased patients with coronavirus disease 2019: retrospective study. BMJ . 2020; 368 :m1091.https://doi.org/10.1136/bmj.m1091 Ge J. The COVID-19 pandemic in China: from dynamic zero-COVID to current policy. Herz . 2023; 48 (3):226-228. https://doi.org/10.1007/s00059-023-05183-5 Burki T. Dynamic zero COVID policy in the fight against COVID. Lancet Respir Med . 2022; 10 (6):e58-e59. https://doi.org/10.1016/S2213-2600(22)00142-4 Bai W, Sha S, Cheung T, et al. Optimizing the dynamic zero-COVID policy in China. Int J Biol Sci . 2022; 18 (14):5314-5316.https://doi.org/10.7150/ijbs.75699 Faust JS, Du C, Liang C, et al. Excess mortality in Massachusetts during the Delta and Omicron waves of COVID-19. JAMA . 2022; 328 (1):74-76. https://doi.org/10.1001/jama.2022.8045 Marquez C, Kerkhoff AD, Schrom J, et al. COVID-19 symptoms and duration of rapid antigen test positivity at a community testing and surveillance site during pre-Delta, Delta, and Omicron BA.1 Periods. JAMA Netw Open . 2022; 5 (10):e2235844. https://doi.org/10.1001/jamanetworkopen.2022.35844 Cai J, Deng X, Yang J, et al. Modeling transmission of SARS-CoV-2 Omicron in China. Nat Med . 2022; 28 (7):1468-1475. https://doi.org/10.1038/s41591-022-01855-7 Shortliffe EH, Sepúlveda MJ. Clinical decision support in the era of artificial intelligence. JAMA . 2018; 320 :2199-2200. https://doi.org/10.1001/jama.2018.17163 Stead WW. Clinical implications and challenges of artificial intelligence and deep learning. JAMA . 2018; 320 :1107-1108. https://doi.org/10.1001/jama.2018.11029 Vaishya R, Javaid M, Khan IH, Haleem A. Artificial Intelligence (AI) applications for COVID-19 pandemic. Diabetes Metab Syndr Clin Res Rev . 2020; 14 :337-339. https://doi.org/10.1016/j.dsx.2020.04.012 Comito C, Pizzuti C. Artificial intelligence for forecasting and diagnosing COVID-19 pandemic: A focused review. Artif Intell Med . 2022; 128 :102286.https://doi.org/10.1016/j.artmed.2022.102286 Theodosiou AA, Read RC. Artificial intelligence, machine learning and deep learning: Potential resources for the infection clinician. J Infect . 2023; 87 (4):287-294.https://doi.org/10.1016/j.jinf.2023.07.006 Magnúsdóttir I, Lovik A, Unnarsdóttir AB, et al. Acute COVID-19 severity and mental health morbidity trajectories in patient populations of six nations: an observational study. Lancet Public Health . 2022; 7 (5):e406-e416.https://doi.org/10.1016/S2468-2667(22)00042-1 Jadhav S, Deng G, Zawin M, Kaufman AE. COVID-view: Diagnosis of COVID-19 using chest CT. IEEE Trans Vis Comput Graph . 2022; 28 (1):227-237.https://doi.org/10.1109/TVCG.2021.3114851 Gorman EA, O'Kane CM, McAuley DF. Acute respiratory distress syndrome in adults: diagnosis, outcomes, long-term sequelae, and management. Lancet . 2022; 400 (10358):1157-1170. https://doi.org/10.1016/S0140-6736(22)01439-8 Kellum JA, Lameire N, Aspelin P, et al. Kidney disease: Improving global outcomes (KDIGO) acute kidney injury work group. KDIGO clinical practice guideline for acute kidney injury. Kidney Int Suppl . 2012; 2 :1-138. https://kdigo.org/wp-content/uploads/2016/10/KDIGO-2012-AKI-Guideline-English.pdf Kidney Disease: Improving Global Outcomes (KDIGO) CKD Work Group. KDIGO 2012 clinical practice guideline for the evaluation and management of chronic kidney disease. Kidney Int Suppl. 2013; 3 (1):1-150. https://kdigo.org/wp-content/uploads/2017/02/KDIGO_2012_CKD_GL.pdf Iba T, Levy JH. Sepsis-induced coagulopathy and disseminated intravascular coagulation. Anesthesiology. 2020; 132 (5):1238-1245. https://doi.org/10.1097/ALN.0000000000003122 Feng Y, Shao H, Gong X, et al. Share 'Dynamic zero-COVID' policy and viral clearance during an omicron wave in Tianjin, China: a city-wide retrospective observational study. BMJ Open . 2022; 12 (12):e066359. https://doi.org/10.1136/bmjopen-2022-066359 Walton M, Murray E, Christian MD. Mental health care for medical staff and affiliated healthcare workers during the COVID-19 pandemic. Eur Heart J Acute Cardiovasc Care . 2020; 9 (3):241-247. https://doi.org/10.1177/2048872620922795 Cheng Z, Tao Y, Liu T, et al. Psychology, stress, insomnia, and resilience of medical staff in China during the COVID-19 policy opening: a cross-sectional survey. Front Public Health . 2023; 11 :1249255. https://doi.org/10.3389/fpubh.2023.1249255 Jamshidi E, Asgary A, Tavakoli N, et al. Using machine learning to predict mortality for COVID-19 patients on day 0 in the ICU. Front Digit Health . 2022; 3 :681608. https://doi.org/10.3389/fdgth.2021.681608 Hartzband P, Groopman J. Physician burnout, interrupted. N Engl J Med. 2020; 382 :2485-2487. https://www.nejm.org/doi/full/10.1056/NEJMp2003149 Liang W, Liang H, Ou L, et al. Development and validation of a clinical risk score to predict the occurrence of critical illness in hospitalized patients with COVID-19. JAMA Intern Med . 2020; 180 (8):1081-1089. https://doi.org/10.1001/jamainternmed.2020.2033 Zhang JJ, Dong X, Liu GH, Gao YD. Risk and protective factors for COVID-19 morbidity, severity, and mortality. Clin Rev Allergy Immunol . 2023; 64 (1):90-107.https://doi.org/10.1007/s12016-022-08921-5 Grasselli G, Greco M, Zanella A, et al. Risk factors associated with mortality among patients with COVID-19 in intensive care units in Lombardy, Italy. JAMA Intern Med . 2020; 180 (10):1345-1355. https://doi.org/10.1001/jamainternmed.2020.3539 Butkiewicz S, Zaczyński A, Hampel M, Pańkowski I, Gałązkowski R, Rzońca P. Analysis of risk factors for in-hospital death due to COVID-19 in patients hospitalised at the temporary hospital located at the national stadium in Warsaw: A retrospective analysis. Int J Environ Res Public Health . 2022; 19 (7):3932. https://doi.org/10.3390/ijerph19073932 Wang Y, Perlman S. COVID-19: Inflammatory profile. Annu Rev Med . 2022; 73 :65-80. https://doi.org/10.1146/annurev-med-042220-012417 Ye Q, Wang B, Mao J. The pathogenesis and treatment of the ‘Cytokine Storm’ in COVID-19. J Infect . 2020; 80 (6):607-613. https://doi.org/10.1016/j.jinf.2020.03.037 Meng M, Chen L, Zhang S, et al. Risk factors for secondary hemophagocytic lymphohistiocytosis in severe coronavirus disease 2019 adult patients. BMC Infect Dis . 2021; 21 (1):398. https://doi.org/10.1186/s12879-021-06094-8 Bivona G, Agnello L, Ciaccio M. Biomarkers for prognosis and treatment response in COVID-19 patients. Ann Lab Med . 2021; 41 (6):540-548. https://doi.org/10.3343/alm.2021.41.6.540 Sun J, Zheng Q, Madhira V, et al. Association between immune dysfunction and COVID-19 breakthrough infection after SARS-CoV-2 vaccination in the US. JAMA Intern Med , 2022; 182 (2):153-162. https://doi.org/10.1001/jamainternmed.2021.7024 Hadid T, Kafri Z, Al-Katib A. Coagulation and anticoagulation in COVID-19. Blood Rev . 2021; 47 :100761. https://doi.org/10.1016/j.blre.2020.100761 Asakura H, Ogawa H. COVID-19-associated coagulopathy and disseminated intravascular coagulation. Int J Hematol . 2021; 113 (1):45-57. https://doi.org/10.1007/s12185-020-03029-y Conway EM, Mackman N, Warren RQ, et al. Understanding COVID-19-associated coagulopathy. Nat Rev Immunol . 2022; 22 (10):639-649. https://doi.org/10.1038/s41577-022-00762-9 Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-4326543","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":305777350,"identity":"f43feda2-107f-4e2a-ae36-be476e1be6d2","order_by":0,"name":"Yuanyuan Pei","email":"","orcid":"","institution":"Peking University People’s Hospital","correspondingAuthor":false,"prefix":"","firstName":"Yuanyuan","middleName":"","lastName":"Pei","suffix":""},{"id":305777351,"identity":"cbf92acb-28fd-463d-937b-c7a101152120","order_by":1,"name":"Xi Wang","email":"","orcid":"","institution":"South China University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Xi","middleName":"","lastName":"Wang","suffix":""},{"id":305777352,"identity":"a7d503ec-4c92-4c04-8eb7-3a4426f0a059","order_by":2,"name":"Lingjie Cao","email":"","orcid":"","institution":"Peking University People’s Hospital","correspondingAuthor":false,"prefix":"","firstName":"Lingjie","middleName":"","lastName":"Cao","suffix":""},{"id":305777353,"identity":"2bfe11a7-3e26-457c-91da-998e9d44a9ff","order_by":3,"name":"Dilu Li","email":"","orcid":"","institution":"Peking University People’s Hospital","correspondingAuthor":false,"prefix":"","firstName":"Dilu","middleName":"","lastName":"Li","suffix":""},{"id":305777354,"identity":"2ef07f54-3d57-4874-81c2-b598b7ce50af","order_by":4,"name":"Liping Guo","email":"","orcid":"","institution":"Peking University People’s Hospital","correspondingAuthor":false,"prefix":"","firstName":"Liping","middleName":"","lastName":"Guo","suffix":""},{"id":305777356,"identity":"f087fb71-596f-4fbe-bba1-4178f67db88b","order_by":5,"name":"Fengtao Yang","email":"","orcid":"","institution":"Peking University People’s Hospital","correspondingAuthor":false,"prefix":"","firstName":"Fengtao","middleName":"","lastName":"Yang","suffix":""},{"id":305777358,"identity":"138f1df6-2d39-4cc3-8c44-90c497ccf4ad","order_by":6,"name":"Wenfeng Huang","email":"","orcid":"","institution":"Peking University People’s Hospital","correspondingAuthor":false,"prefix":"","firstName":"Wenfeng","middleName":"","lastName":"Huang","suffix":""},{"id":305777360,"identity":"6b470525-5371-417b-b921-1a6abe24b556","order_by":7,"name":"Hao Li","email":"","orcid":"","institution":"Peking University People’s Hospital","correspondingAuthor":false,"prefix":"","firstName":"Hao","middleName":"","lastName":"Li","suffix":""},{"id":305777361,"identity":"fb387aac-7d34-4250-8172-3910291f4912","order_by":8,"name":"Jing He","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3UlEQVRIie3PsQrCQAyA4bi0S0o3uaLQV6g4qCD4KldcKzh2koLiVJwrvoSjY8qBLudeqKDiCwguIh20g472RsH7t0A+SAB0uh/MA+AEwNBwBdE1VCfdps0MP02kGikL+06CbWHNFEjHjM5i/GDo5fGVrAhcu07fSS8mLpaLFzns1+RsoLVc8YrDMs6FFb8IjdbUksC9vIocT28SnMifq5AMuMA7QycJgFIlIsvDIoY2br00kkzhl50c3rCYDAxzerkVYd+1GxUEADnU5p+JVa2XmQRQqCzqdDrd3/YEkAlOkDz/MTYAAAAASUVORK5CYII=","orcid":"","institution":"Peking University People’s Hospital","correspondingAuthor":true,"prefix":"","firstName":"Jing","middleName":"","lastName":"He","suffix":""},{"id":305777363,"identity":"733d1fc3-07df-495e-a84c-4ce08213a506","order_by":9,"name":"Jihong Zhu","email":"","orcid":"","institution":"Peking University People’s Hospital","correspondingAuthor":false,"prefix":"","firstName":"Jihong","middleName":"","lastName":"Zhu","suffix":""}],"badges":[],"createdAt":"2024-04-26 01:38:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4326543/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4326543/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":57708070,"identity":"aeed11a9-792b-448e-be41-295ea5b31937","added_by":"auto","created_at":"2024-06-04 15:15:33","extension":"jpg","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":463823,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eDisease Composition Among Critically Ill Patients\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"1.jpg","url":"https://assets-eu.researchsquare.com/files/rs-4326543/v1/99c9e5049709d327cb7ae147.jpg"},{"id":57708884,"identity":"37a42f3a-ce5e-4eed-ba47-180f87b88956","added_by":"auto","created_at":"2024-06-04 15:23:33","extension":"jpg","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":657430,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eNumber of Daily Emergency Room Visits by Daily Consulting Patients\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"2.jpg","url":"https://assets-eu.researchsquare.com/files/rs-4326543/v1/dd7de97f65799eb62e490607.jpg"},{"id":57708071,"identity":"96674cbf-af8a-4023-b0e2-0be562012d4d","added_by":"auto","created_at":"2024-06-04 15:15:33","extension":"jpg","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":576977,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eNumber of Daily Emergency Room Visits by Critically Ill Patients\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"3.jpg","url":"https://assets-eu.researchsquare.com/files/rs-4326543/v1/6b25e6e3bd7d7ea2ecfe580f.jpg"},{"id":57708076,"identity":"48ec87a6-e0d0-42d4-a7e1-698dfb4af1ab","added_by":"auto","created_at":"2024-06-04 15:15:34","extension":"jpg","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":464529,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eMachine learning model performance (a) Histogram of Area Under the Curve (AUC) Scores Across Models (b) Receiver Operating Characteristic (ROC) Curve for the Random Forest (RF) Model.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"4.jpg","url":"https://assets-eu.researchsquare.com/files/rs-4326543/v1/42774a995c0fee220a3ec92a.jpg"},{"id":57708075,"identity":"67f53160-47ea-4af0-8ea6-02401533bd5f","added_by":"auto","created_at":"2024-06-04 15:15:34","extension":"jpg","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":498476,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eTop 15 Important Risk Factors\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"5.jpg","url":"https://assets-eu.researchsquare.com/files/rs-4326543/v1/13368399e31e1a4c4608c985.jpg"},{"id":57708073,"identity":"ffdbc79a-8721-4b70-a1ea-79ac4629fffe","added_by":"auto","created_at":"2024-06-04 15:15:33","extension":"jpg","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":436244,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eCOVID-19 Emergency clinical risk prediction Graphical User Interface\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"6.jpg","url":"https://assets-eu.researchsquare.com/files/rs-4326543/v1/d0d0bd1b04c7c5de4e85ee7c.jpg"},{"id":62011037,"identity":"87bf8960-685b-4bae-9264-091939fb2a1b","added_by":"auto","created_at":"2024-08-08 07:45:43","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4204780,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4326543/v1/1b9776fd-2ba1-45fe-9f64-dc636d8436a1.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Impact analysis and predictive modeling in emergency care： Evaluating the effects of immediately post-COVID-19 lockdown at a top Chinese teaching hospital","fulltext":[{"header":"Key Points","content":"\u003cp\u003eQuestion: For a long period, China implemented extensive lockdowns for COVID-19, insights into the post COVID-19-lockdown era remain sparse. \u0026nbsp;\u003c/p\u003e\n\u003cp\u003eFindings: In this study of 25413 patients who visited ED, of whom 631 patients were critically ill. To identify key predictors of mortality in critical patients, machine learning was utilized. The study developed a predictive model with a graphical user interface (GUI) that could accurately predict the prognosis of critical patients.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eMeaning: Our findings highlight the significant impact of the post COVID-19-lockdown period on ED. The development of a predictive model is consequential for enhancing decisions and medical resources distribution in ED care.\u003c/p\u003e"},{"header":"Introduction","content":"\u003cp\u003eCoronavirus disease of 2019 (COVID-19) is a disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), has resulted in a global pandemic. \u003csup\u003e1,2\u003c/sup\u003e Over 760\u0026nbsp;million cases and 6\u0026middot;9\u0026nbsp;million deaths have been recorded worldwide, but the actual number is thought to be higher.\u003csup\u003e1,2\u003c/sup\u003e The initial outbreak in December 2019 consisted of 27 patients with pneumonia in Wuhan, Hubei Province, China.\u003csup\u003e3\u003c/sup\u003e Then the virus spread around the world with great rapidity and was immediately declared as a pandemic.\u003csup\u003e1\u0026ndash;3\u003c/sup\u003e\u003c/p\u003e \u003cp\u003eThe pandemic necessitated the implementation of stringent lockdown measures worldwide, with China being one of the first countries to impose such restrictions.\u003csup\u003e4\u0026ndash;6\u003c/sup\u003e Neverthless, as the virus continues to mutate, especially the Delta and Omicron variants, have resulted in a series of local outburst in China.\u003csup\u003e4,7\u0026ndash;9\u003c/sup\u003e Accordingly, China liberalized its control of COVID-19 at the end of 2022. The call off of the lockdown marked a critical transition in the management of the pandemic. Healthcare systems, particularly emergency services, faced the dual challenge of managing a potential resurgence of COVID-19 cases and addressing the backlog of non-COVID medical needs that had accumulated during the lockdown. This study examines the aftermath of reducing the COVID-19 lockdown in the emergency department (ED) of a top teaching hospital in China, focusing on the impact on patient care and outcomes, and provides a unique opportunity to study the dynamics of healthcare delivery during a post-lockdown period. Meanwhile, it also offers a comprehensive view of the challenges and adaptations in a high-volume ED environment. By predictive analytics, this study aims to assess the impact of post-COVID-19 lockdown on patient inflow, disease spectrum, complications, laboratory indicators, and prognostic factor, as well as COVID-19 pneumonia. This approach is especially useful in emergency care, where timely and efficient response is essential. Recently, progress in artificial intelligence (AI) technology for disease screening indicate potential as computer-aided diagnosis and prediction tools.\u003csup\u003e10\u0026ndash;14\u003c/sup\u003e AI might represent a novel and useful technology for the management of critical patients to quickly predict mortality, which helps to risk stratify patients and provide targeted treatment according to different groups. A robust predictive model is developed in this study to help in planning and optimizing emergency care services in the face of healthcare challenges after COVID-19 lockdown.\u003c/p\u003e \u003cp\u003eTherefore, this study provides a vital analysis of the effects of lifting the COVID-19 lockdown on emergency healthcare services, while exploring how predictive analytics can enhance the response to future healthcare crises.\u003c/p\u003e"},{"header":"Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003eStudy population\u003c/h2\u003e \u003cp\u003eFrom December 2022 to January 2023, all patients admitted to ER, Peking University People\u0026rsquo;s Hospital in China were enrolled in this observational study.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003eProcedures\u003c/h2\u003e \u003cp\u003eFirstly, we observed the dynamic change of numbers of daily emergency consulting room visits, who were patients with mild and moderate symptoms. Then we divided the patients into four subgroups to analyze the changes in the number of visits, including internal emergencies, surgical emergencies, gynecological emergencies, and other emergencies (otolaryngology and ophthalmology), respectively.\u003c/p\u003e \u003cp\u003eNext, we surveyed the total number of critically ill patients admitted to the emergency resuscitation room every day, and analyze the spectrum of underlying diseases, including COVID-19 severe pneumonia, severe pneumonia not caused by COVID-19, cardiovascular emergencies (acute myocardial infarction and acute heart failure), gastrointestinal system emergencies (gastrointestinal bleeding, severe pancreatitis, cirrhosis), central nervous system emergencies (cerebral hemorrhage, subarachnoid hemorrhage and acute cerebral infarction), hematological emergencies (acute leukemia, hemophagocytic syndrome, severe anemia, and so on), endocrine system emergencies (hyperglycemic crisis, hypoglycemic coma), sepsis, sudden death, surgical emergencies, rheumatological emergencies and other causes.\u003c/p\u003e \u003cp\u003eFurthermore, we collected baseline characteristics data from all critical patients admitted to the emergency resuscitation room. Demographic data including age, sex, comorbidities (hypertension, diabetes mellitus, coronary heart disease, heart failure, asthma, chronic obstructive pulmonary disease, interstitial lung disease, chronic kidney disease, cerebral diseases, hematological diseases, rheumatic diseases and immunosuppression state), time from onset to admission (day) and initial vital signs were collected. Meanwhile, we assessed complications including acute respiratory distress syndrome (ARDS), respiratory failure, acute myocardial injury, acute liver injury (ALI), acute kidney injury (AKI), hyperfunction of the fibrinolysis and disseminated intravascular coagulation (DIC). In addition, laboratory indicators included levels of white blood cell, hemoglobin, and platelet counts, C-reactive protein (CRP), procalcitonin (PCT), interleukin-6 (IL-6), lactate, hypersensitive troponin I (hsTNI), brain natriuretic peptide(BNP), aspartate transaminase (AST), alanine transaminase (ALT), total bilirubin, direct bilirubin, albumin, blood urea nitrogen(BUN), creatinine, estimate glomerular filtration rate (eGFR), serum triglyceride, prothrombin time (PT), activated partial thromboplastin time (APTT), fibrinogen, fibrinogen degradation products (FDP), and D-dimer levels. Drug and supportive treatment include the use of antibiotics, glucocorticoids, baricitinib, tocilizumab, gamma globulin, oxygen therapy, noninvasive ventilation, mechanical ventilation and extracorporeal membrane oxygenation (ECMO) were recorded accordingly. Each record was checked independently by 2 clinicians.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003eDefinitions\u003c/h2\u003e \u003cp\u003eCOVID-19 diagnoses were confirmed by positive antigen testing and/or high throughput sequencing or real-time reverse-transcription polymerase-chain-reaction (RT-PCR) assay or for nasal and pharyngeal swab specimens, with typical imaging manifestations by chest CT.\u003csup\u003e15,16\u003c/sup\u003e ARDS was diagnosed according to the Berlin definition, including acute onset (within 7 days of new or worsening respiratory symptoms), bilateral radiographical opacities that are not fully explained by effusion, atelectasis or masses, arterial hypoxemia, identified risk factor for ARDS and not exclusively due to cardiac causes.\u003csup\u003e17\u003c/sup\u003e Respiratory failure is defined as arterial oxygen partial pressure\u0026thinsp;\u0026lt;\u0026thinsp;60mmHg in the non-oxygenated state. Transaminase\u0026thinsp;\u0026ge;\u0026thinsp;3 fold the normal upper limit is defined as acute liver injury (ALI). Myocardial injury was diagnosed according to the elevation of cardiac hypersensitive troponin I. Acute kidney injury (AKI) is characterized by an increase in serum creatinine of 0\u0026middot;3 mg/dl within 48 h, an elevation on to 1\u0026middot;5 fold the baseline level within the first 7 days, or a decline in urine output to not more than 0\u0026middot;5mL/kg per hour for at least 6 hours in accordance with 2012 KDIGO definition.\u003csup\u003e18\u003c/sup\u003e CKD was defined according to the definition of the National Kidney Foundation as kidney damage or eGFR of less than 60 ml/min per 1\u0026middot;73 m\u003csup\u003e2\u003c/sup\u003e for at least 3 months.\u003csup\u003e19\u003c/sup\u003e Hyperfunction of the fibrinolysis system was confirmed by the obvious increase of fibrinogen, FDP and D-dimers. DIC was diagnosed according to the International Society on Thrombosis and Haemostasis scientific standardization subcommittee, including elevated levels of fibrin-related markers such as fibrin/FDP or D-dimers, decreased platelet counts, prolonged prothrombin time, and decreased fibrinogen levels.\u003csup\u003e20\u003c/sup\u003e\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003eData processing\u003c/h2\u003e \u003cp\u003eIn this retrospective investigation, we focused on a cohort of 631patients, encompassing a total of 99 variables, including both laboratory and clinical data. All variables were tested for normal distribution using the Kolmogorov-Smirnov test. All descriptive statistics are summarized and shown as mean\u0026thinsp;\u0026plusmn;\u0026thinsp;standard deviation or median (25\u0026ndash;75%). Patients with integral clinical data stands at 581, providing the basis for descriptive statistical analysis.\u003c/p\u003e \u003cp\u003eA stringent data cleansing protocol was applied before finalizing the dataset for the machine learning model. Where a feature had more than 50% of missing values or when more than 50% of a patient's features were missing, we will proceed to remove variables or patients, resulting in a refined cohort of 550 cases. In the realm of the existing dataset, a methodological approach of interpolation has been systematically employed to impute the precise data points. For numerical features, we employed Bayesian linear regression, while binary variables were imputed using logistic regression. As a result, we obtained a dataset consisting of 82 variables and 550 patient records for model development and validation. To assess the model's performance, we randomly allocated 20% of the data for testing and verification purposes. The data imputation procedures were carried out using the R programming language in this study.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003eMosdel development and feature selection\u003c/h2\u003e \u003cp\u003eWe used the random forest (RF), support vector machine (SVM), linear discriminant analysis (LDA), Gaussian Naive Bayes (GaussianNB), logistic regression (LR), and Multilayer Perceptron (MLP) for prediction. The model's accuracy was assessed using the area under the receiver-operator curve (AUC). We utilized AUC to compare the accuracy of these six machine learning models and selected the optimal model for identifying the top 15 variables contributing most significantly to the prediction. To reduce the model's feature space dimensionality, we exclusively employed these 15 parameters with the highest predictive values to train the model and design the software. Additionally, we conducted further comparisons and validation of machine learning methods, documenting their AUC, accuracy, precision, F1-score, and specificity. All machine learning algorithms were implemented using the Python programming language in this study.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003eThe construction of the Graphical User Interface (GUI)\u003c/h2\u003e \u003cp\u003eThe Graphical User Interface (GUI) construction involved utilizing Python's PyQt5 library for user interaction. This interface integrated input fields and buttons to receive user data. The data underwent processing and was inputted into a pre-trained classifier. The resultant predictions, probability scores, and labels were then displayed for user interpretation, serving to enhance accessibility for managing critical COVID-19 cases in emergency settings.\u003c/p\u003e \u003c/div\u003e"},{"header":"Results","content":"\u003cdiv id=\"Sec10\" class=\"Section2\"\u003e \u003ch2\u003eOverview of patient demographics and clinical characteristics\u003c/h2\u003e \u003cp\u003eOverall, a total of 24792 patients were enrolled in the emergency consulting room in two months between December 6, 2022 and January 31, 2023. Meanwhile, 631 critically ill patients admitted to the emergency resuscitation room during this period, and in-hospital mortality was 32\u0026middot;2% (203/631).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eAs shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e, We further analyzed the underlying disease composition of all critically ill patients. Among all causes, the proportion of COVID-19 was 59\u0026middot;59% (n\u0026thinsp;=\u0026thinsp;376), which is predominant, acute cardiovascular diseases was 7\u0026middot;61% (n\u0026thinsp;=\u0026thinsp;48), gastrointestinal emergencies was 5\u0026middot;71% (n\u0026thinsp;=\u0026thinsp;36), pneumonia not caused by COVID-19 was 5\u0026middot;23% (n\u0026thinsp;=\u0026thinsp;33), central nervous system emergencies was 4\u0026middot;91% (n\u0026thinsp;=\u0026thinsp;31), sudden death was 3\u0026middot;01% (n\u0026thinsp;=\u0026thinsp;19), hematological system emergencies was 2\u0026middot;69% (n\u0026thinsp;=\u0026thinsp;17), endocrine system emergencies was 1\u0026middot;74% (n\u0026thinsp;=\u0026thinsp;11), surgical emergencies was 1\u0026middot;74% (n\u0026thinsp;=\u0026thinsp;11), sepsis was 1\u0026middot;11% (n\u0026thinsp;=\u0026thinsp;7), rheumatic immune system emergency was 0\u0026middot;63% (n\u0026thinsp;=\u0026thinsp;4), and other causes 6\u0026middot;02% (n\u0026thinsp;=\u0026thinsp;38), respectively.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec11\" class=\"Section2\"\u003e \u003ch2\u003eDynamic changes in daily emergency room visits post COVID-19 lockdown\u003c/h2\u003e \u003cp\u003eAs displayed in Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e, the total number of daily visits to the emergency consulting room showed a progressive elevation during the whole December post COVID-19 lockdown. The number of daily consultations rose from 270 at the beginning to over 600 progressively, peaked at 668 on December 30, and then showed a gradual decline, eventually returning to the initial baseline levels.\u003c/p\u003e \u003cp\u003eIn contrast, January experienced a reduction in medical emergencies but observed a gradual increase in surgical emergency. The frequency of gynecological and other types of emergencies remained consistent during this period.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec12\" class=\"Section2\"\u003e \u003ch2\u003eDisease composition in critically ill patients\u003c/h2\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e illustrates a comparison between the trends in emergency critically ill patient admissions and the trends in consultations following the lockdown. The daily numbers of critical patients admitted to ED were less than 10 cases at the beginning (from December 6 to December 10), and then gradually went up, reaching a peak of 29 cases on January 2. After reaching the peak, it fluctuated down and returned to the initial level by the end of January. Among them, the daily numbers of critically ill patients are significantly correlated with the daily numbers of patients with pneumonia. In terms of underlying disease distribution, COVID-19 pneumonia patients accounted for the largest proportion of the whole critically ill patients, up to 59\u0026middot;6%. Meanwhile, the proportion of other common critical diseases in the ED, such as cardiovascular emergencies, gastrointestinal emergencies and central nervous system emergencies, is all below 10% respectively, which has been indicated in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec13\" class=\"Section2\"\u003e \u003ch2\u003eProfile of critically ill patients\u003c/h2\u003e \u003cp\u003eIn the cohort, we collected data from all 631 critical patients. After excluding patients with excessive incomplete data, 581 patients were finally enrolled. Overall, the mean (SD) age of patients in this cohort was 80 (68, 87) years, 346 patients (59\u0026middot;6%) were men and 376 patients (64\u0026middot;7%) had severe COVID-19 pneumonia. In terms of coexisting condition, the proportion of hypertension, diabetes, coronary heart disease, cerebral diseases, CKD, heart failure, hematological diseases was 36\u0026middot;1% (210 patients), 40\u0026middot;0% (231 patients), 30\u0026middot;0% (173 patients), 28\u0026middot;6% (165 patients), 20\u0026middot;0% (116 patients), 12\u0026middot;8% (74 patients), 12\u0026middot;6% (73 patients), respectively. About complications, the incidence of ARDS, respiratory failure, AKI, acute myocardial injury, ALI, fibrinolytic hyperfunction, DIC and acute confusion was 28\u0026middot;8% (109 patients), 54\u0026middot;4% (252 patients), 34\u0026middot;5% (178 patients), 38\u0026middot;0% (189 patients), 24\u0026middot;6% (130 patients), 18\u0026middot;4% (96 patients), 12\u0026middot;9% (67 patients) and 23% (120 patients) accordingly. These baseline characteristics were shown in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eBaseline characteristics of the patients in different outcomes groups\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eVariables\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTotal (n\u0026thinsp;=\u0026thinsp;581)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eRemission\u003c/p\u003e \u003cp\u003egroup (n\u0026thinsp;=\u0026thinsp;378)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eDeath group (n\u0026thinsp;=\u0026thinsp;203)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003eP\u003c/em\u003e value\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDemographic data\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAge(years)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e80(68,87)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e77(64, 86)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e82(73,88)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.000\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\u003e346(59.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e211(55.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e135(66.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.013\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eCOVID-19 pneumonia (%)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e376(64.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e211(55.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e165(81.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.024\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eTime from onset to admission (day)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e5(\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e, \u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4(\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e, \u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e5(\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e, \u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.419\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eLength of hospitliztion (day)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e8(\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e, \u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e10(\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e, \u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e4(\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e, \u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.000\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eComorbidities (%)\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 \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHypertension\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e210(36.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e231(61.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e137(67.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.147\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDiabetes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e231(40.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e152(40.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e79(39.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.859\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCoronary heart disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e173(30.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e107(28.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e66(32.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.295\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHeart failure\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e74(12.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e50(13.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e24(11.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.696\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCerebral diseases\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e165(28.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e101(26.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e64(31.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.210\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCOPD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e28(4.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e21(5.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e7(3.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.314\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAsthma\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e21(3.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e12(3.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e9(4.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.485\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eInterstitial lung disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e25(4.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e14(3.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e11(5.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.390\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCKD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e116(20.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e67(17.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e49(24.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.064\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHematological diseases\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e73(12.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e56(14.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e17(8.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.035\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRheumatic diseases\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e38(6.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e26(6.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e12(5.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.727\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eImmunosuppression state\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e57(9.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e37(9.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e20(10.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eVital signs\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 \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSBP (mmHg)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e137(118,156)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e138(118,156)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e134(119,160)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.841\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDBP (mmHg)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e75(65,87)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e75(65,87)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e74(65,87)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.536\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSpO2 (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e88(80,94)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e90(81,95)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e86(75,92)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.002\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTmax (℃)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e38.5(37.7,39.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e38.2(37.9,39.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e38.5(37.6,39.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.792\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eComplications (%)\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 \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eARDS\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e109(28.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e68(28.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e41(29.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.907\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRespiratory failure\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e252(54.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e149(51.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e103(59.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.123\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAKI\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e178(34.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e109(32.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e69(37.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.335\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAcute myocardial injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e189(38.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e113(35.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e76(42.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.063\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eALI\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e130(24.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e83(24.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e47(25.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.833\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFibrinolytic hyperfunction\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e96(18.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e55(16.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e41(22.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.066\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDIC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e67(12.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e37(11.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e30(16.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.062\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAcute confusion\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e120(\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e78(22.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e42(23.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1.000\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\u003eFurthermore, all critical emergencies were divided into the discharge group and in-hospital death group for univariate analysis. The results indicated that in-hospital death group were older, with more male and more percentage of COVID-19 pneumonia. Meanwhile, the death group tended to have lower SpO2 at admission, decreased WBC levels, as well as elevated CRP, IL-6, BUN, FDP, D-dimer and Lac levels. In terms of treatments, the death group had more proportion of oxygen therapy, noninvasive and mechanical ventilation. In addition, we found that although there was no statistical difference in complications such as acute myocardial injury, fibrinolytic hyperfunction and DIC between the groups, their incidence was still obviously increased in the death group, with \u003cem\u003eP\u003c/em\u003e values from 0\u0026middot;062 to 0\u0026middot;066. Laboratory findings and treatments were presented in Tables\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e and \u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eLaboratory characteristics of the patients in different outcomes groups\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eVariables\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTotal (n\u0026thinsp;=\u0026thinsp;581)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eRemission\u003c/p\u003e \u003cp\u003egroup (n\u0026thinsp;=\u0026thinsp;378)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eDeath group (n\u0026thinsp;=\u0026thinsp;203)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003eP\u003c/em\u003e value\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePeak WBC (*10\u003csup\u003e9\u003c/sup\u003e/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e10.5(7.7, 15.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e10.6(7.3,15.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e10.5(8.2,15.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.558\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNadiral WBC(*10\u003csup\u003e9\u003c/sup\u003e/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e6.4(4.5, 9.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e6.2(4.1,8.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e6.7(5.0,9.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.010\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHemoglobin(g/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e108(86, 126)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e108(86, 126)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e112(88, 127)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.130\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePlatelets(*10\u003csup\u003e9\u003c/sup\u003e/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e181(126, 249)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e181(126, 249)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e175(118,226)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.304\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCRP (mg/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e75.8(25.0, 140.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e62.9(15.8,130.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e91.1(39.2, 152.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePCT (ng/ml)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.39(0.122, 1.67)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.35(0.12, 1.78)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.42(0.12, 1.53)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.976\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAST (U/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e38(24,71)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e37(22, 70)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e39(27, 77)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.358\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eALT (U/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e27(15,49)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e26(15, 53)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e27(16, 45)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.647\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTbil (mmol/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e12.4(8.4,19.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e12.4(8.4,19.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e12.8(8.4, 20.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.350\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDbil (mmol/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e5.9(3.7,9.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e5.8(3.7, 8,8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e6.0(3.7,10.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.456\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTriglyceride (mmol/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.49(1.09, 2.07)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.50(1.08, 2.05)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.45(1.10, 2.07)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.997\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAlbumin (g/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e30.7(27.0,36.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e30.8(26.7,36.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e30.7(27.4, 36.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.639\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBUN (mmol/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e11.8(7.3, 22.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e11.0(6.9, 21.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e13.9(8.3, 23.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.020\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSCr (\u0026micro;mol/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e106(75, 195)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e106(75, 195)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e112(80,221)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.087\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eeGFR (ml/min*1.73m\u003csup\u003e2\u003c/sup\u003e)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e53.04(24.91,80.76)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e56.24(26.98, 81.94)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e48.59(21.53, 78.49)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.101\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ehsTNI\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e46.2(13.3,254.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e43.4(12.1, 299.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e55.6(15.2,222.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.871\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBNP\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e276(114,824)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e256(102, 868)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e181(157, 769)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.355\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePeak FIB (mg/dl)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e441(361,522)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e432(357, 514)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e459(378,530)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.071\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNadiral FIB (mg/dl)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e341(249, 432)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e336(253,420)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e367(243,465)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.160\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePeak PT (s)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e12.7(11.5,14.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e12.7(11.6,15.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e12.7(11.4,14.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.349\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePeak APTT (s)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e31.4(28.7, 35.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e31.4(28.7, 35.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e31.6(28.7, 36.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.906\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePeak D-dimer (ng/ml)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1129(514,3723)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1065(473, 3353)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1713(553,5629)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.022\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePeak FDP (ug/ml)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e8.1(3.9,27.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7.4(3.5, 21.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e11.4(4.6, 41.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.005\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLac (mmol/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2.2(1.3,3.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2.1(1.3, 3.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e2.7(1.5,5.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.028\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFerritin (ng/ml)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e796(430, 1306)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e659(324, 1337)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e870(464, 1173)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.318\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eIL-6 (pg/ml)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e51.8(19.4, 180)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e41.9(13.3, 118)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e92.6(39.3, 322)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.003\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\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\u003eTreatments in the patients of different outcome groups\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"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 \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTreatments (%)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTotal (n\u0026thinsp;=\u0026thinsp;581)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eDischarge\u003c/p\u003e \u003cp\u003egroup (n\u0026thinsp;=\u0026thinsp;378)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eDeath group (n\u0026thinsp;=\u0026thinsp;203)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003eP\u003c/em\u003e value\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCarbapenems\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e312(59.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e197(58.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e115(60.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.712\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePenicillin\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e98(18.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e24(40.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e52(51.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.195\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCephalosporin\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e116(22.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e75(22.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e41(21.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.913\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eQuinolone\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e41(21.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e24(7.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e17(9.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.498\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAminoglycosides\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e98(18.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e66(19.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e32(16.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.486\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTetracycline\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e14(2.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e11(3.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e3(1.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.398\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFungal antibiotics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e41(7.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e24(7.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e17(9.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.498\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBaritinib\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e13(2.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e7(2.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e6(3.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.560\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTocilizumab\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e4(0.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2(0.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2(1.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.621\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eImmunoglobulin\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e45(8.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e30(8.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e15(7.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.748\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGlucocorticoids\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e197(37.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e118(35.0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e79(41.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.133\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOxygen therapy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e477(82.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e292(77.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e185(91.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.000\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMechanical ventilation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e55(9.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e9(2.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e46(22.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.000\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNoninvasive ventilation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e140(24.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e55(14.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e85(42.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.000\u003c/p\u003e \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=\"Sec14\" class=\"Section2\"\u003e \u003ch2\u003eResource utilization and hospital capacity\u003c/h2\u003e \u003cp\u003eDuring the post-COVID-19 lockdown period, there was a notable fluctuation in bed occupancy rates within the ED and across the hospital. The data indicates a significant increase in bed utilization, rising from 85\u0026thinsp;~\u0026thinsp;92% in the pre-lockdown phase to 100% post-lockdown. The distribution of resources, particularly ventilators and intensive care unit (ICU) beds, was significantly impacted. The demand for ventilators increases from 50\u0026ndash;75\u0026ndash;100% of available units, underscoring the severity of respiratory complications in COVID-19 cases.\u003c/p\u003e \u003cp\u003eIn response to these demands, the hospital re-allocated resources, converting general wards into COVID-19 units and increasing the number of beds in the ICU by 200%. These adjustments were critical in managing the heightened patient load while ensuring care for both COVID-19 and non-COVID-19 emergencies. The post-lockdown period necessitated significant adjustments in staffing within the ED. The staffing in the ED was increased by 250%, with a notable emphasis on recruiting internal specialists in infectious diseases, pulmonology, and critical care. These adaptations demonstrate the significance of healthcare systems that are both adaptable and responsive in the face of pandemics and large-scale public health emergencies.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec15\" class=\"Section2\"\u003e \u003ch2\u003eDevelopment and evaluation of the predictive model\u003c/h2\u003e \u003cp\u003eIn this study, we developed six machine learning models as described in the \u003cspan refid=\"Sec2\" class=\"InternalRef\"\u003eMethods\u003c/span\u003e section, and assessed their performance using scores from an independent test set based on AUC, Accuracy, Precision, F1-score, and Specificity Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e: Machine learning performance, which is a comparison of Model Performance Metrics: Area Under the Curve (AUC), Accuracy, Precision, F1-Score, and Specificity for Random Forest (RF), Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), Logistic Regression (LR), Gaussian Naive Bayes (GaussianNB), and Multilayer Perceptron (MLP). The Random Forest algorithm demonstrated as the the highest AUC score among the models (Figure. 4, a and b). In the selection of risk factors, we utilized the Gini coefficient from Random Forest as the criterion which in Random Forests gauges each feature's impact on prediction accuracy, amalgamating insights from multiple trees. Its use ensures reliability by mitigating overfitting risks and captures complex variable interactions, providing crucial insights for clinical predictions. After the model training, top 15 variables have been selected as significant predictors of critical illness, including mechanical ventilation, age, SPO2, WBC nadir, CRP peak, non-invasive ventilation, SBP, APTT peak, WBC peak, DBP, Direct bilirubin peak, PT peak, FIB nadir, FIB peak, and PLT nadir were determined as risk factors for patient mortality (Figure. 5). It is worth noting that COVID-19 was not selected as one of the top 15 fatal factors.\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\u003eMachine learning performance\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"7\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eRandomForest\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eLda\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eSVM\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eLR\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eGaussianNB\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003eMLP\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAUC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.8385\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.7585\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.7593\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.7259\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.7463\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.7092\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAccuracy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.7545\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.6818\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.6909\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.7091\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.609\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.6727\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePrecision\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.7519\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.6643\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.6758\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.6959\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.7047\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.6560\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eF1-score\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.7359\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.6545\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.6667\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.6848\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.6119\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.6586\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSpecificity\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.9167\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.8732\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.8732\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.8889\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.4930\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.8194\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\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec16\" class=\"Section2\"\u003e \u003ch2\u003eModel accuracy and clinical application\u003c/h2\u003e \u003cp\u003eAfter identifying the 15 risk factors, we refined the model to avoid redundancy, we focusing on the key indicators for the prediction of mortality. The final performance of the model demonstrated that the Random Forest algorithm maintained the highest-performing model with an AUC of 0\u0026middot;8385.\u003c/p\u003e \u003cp\u003eFinally, to translate these analytical advancements into practical clinical tools, we developed a user-friendly Graphical User Interface (GUI). This GUI embodies the essence of our predictive algorithms, offering a streamlined and accessible interface for real-time application in clinical settings, particularly for managing critical cases of COVID-19 in emergency departments (Figure. 6). It provides clinicians with an efficient, intuitive tool to aid in decision-making processes. The software, designed for local use, is built upon the sklearn library in Python and features a PyQt5 graphical interface, ensuring both reliability and ease of use in a demanding healthcare environment.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e"},{"header":"Discussion","content":"\u003cp\u003eAccording to our findings, there has been a significant increase in emergency department (ED) visits, especially for patients with COVID-19 pneumonia who are critically ill. The entire period lasted about 2 months, a total of 25423 patients visited the ED, including 631 critically ill patients. Initially, there was a significant increase in both general and critical emergencies, with general cases mainly involving internal ailments and critical cases mainly involving severe COVID-19 pneumonia. The peak lasted for approximately 20 days, and daily consultations reached a high of 668 on December 30 and remained above 500 for 14 days. As internal emergencies decreased and surgical cases rose, visit numbers returned to normal by late January 2023. This surge underscores the ongoing challenges in healthcare systems in managing pandemic-related cases alongside routine emergencies.\u003c/p\u003e \u003cp\u003eIn consistent with the health and medical care situation faced by other countries and regions, ED has faced a variety of serious stiff issues during the whole break period, including the shortage of medical resources, the infection of the medical health team, overloaded and sustained high intensity work state, effort-reward imbalance.\u003csup\u003e22,23\u003c/sup\u003e As previously mentioned, bed occupancy, oxygen and ventilators shortage are both highly intense in the ED. Under this broad environment of epidemic, our hospital has taken a series of immediate measures to alleviate the scarce resources, including bed utilization, ICU bed expansion, establishment and conversion of COVID-19 units, the assignment and supportment of ED staff. These adjustments have revealed the adaptation and responsibility of healthcare systems is crucial when facing a major public health crisis.\u003c/p\u003e \u003cp\u003eIn addition to the overall macroscopical controlment, it is also vital to seek a reasonable and reliable rapid diagnosis and prediction tool, for the optimized diagnosis and therapies of the total critical patients. Computational assistance has indicated its advantage to ED care providers, who under high tension and exhaustion might lead to a decline in the accuracy of clinical judgment, resulting in increased mortality rates.\u003csup\u003e24,25\u003c/sup\u003e Beyond the general benefits of data-driven decision-making, AI could help clinical professionals determine who needs a critical level of care more precisely.\u003c/p\u003e \u003cp\u003eIn this study, we employed a novel machine-learning method using routine clinical and laboratory data to predict mortality in critically ill patients in the Emergency Department during an epidemic outbreak. This is the first study of its kind to develop a mortality prediction risk model for Chinese ED patients, predominantly affected by COVID-19. Meanwhile, the six machine learning models were trained and tested to find the optimal model and used the gini coefficient to screen risk factors to increase the interpretability of the model. Furthermore, we developed and validated a software-based risk calculator t perform risk scoring and predict the development of critical illness among ED patients. The performance of this risk score was satisfactory with accuracy based on a reliable AUROC as 0\u0026middot;8385 and 15 variables were included, which has the capability to accurately discern patients' likelihood of survival or mortality. The predictive model developed in this study demonstrates high accuracy, suggesting its potential as a valuable asset in emergency care protocols. It is found that all critical emergencies were elder people predominantly, and age is a risk factor for poor prognosis, which is consistent with previous studies.\u003csup\u003e24,26\u0026ndash;28\u003c/sup\u003e Patients with lower SpO2 and treated with noninvasive ventilation and mechanical ventilation tended to have a higher mortality for the severe respiratory dysfunction.\u003csup\u003e24,28,29\u003c/sup\u003e Elevated direct bilirubin has also been found to be associated with poor studies in several studies, which is consistent with our study.\u003csup\u003e26\u003c/sup\u003e\u003c/p\u003e \u003cp\u003eCytokine storms are well-known to play an important role in the pathophysiological process of COVID-19.\u003csup\u003e27,30,31\u003c/sup\u003e Persistent high inflammatory state and immune dysfunction have been found to be associated with increased mortality in numerous studies.\u003csup\u003e30\u0026ndash;33\u003c/sup\u003e The proinflammatory state can be manifested as a significant elevation in WBC, ferritin, CRP, IL-6, IL-1 and other inflammatory cytokine. On the other side, the immune dysfunction is accompanied by a decrease in WBC and lymphocyte counts, which leads to an increase in secondary and opportunistic infections.\u003csup\u003e33,34\u003c/sup\u003e This phenomenon has also been observed in this study.\u003c/p\u003e \u003cp\u003eThe disturbance of coagulation system is a common and critical complication in COVID-19 patients.\u003csup\u003e35\u0026ndash;37\u003c/sup\u003e All coagulation and fibrinolysis parameters can be affected by COVID-19, including APTT, PT, fibrinogen, FDP, D-dimer and platelet count, which is called COVID-19 induced coagulopathy in the early stage, and with the progression of the disease, it can develop into DIC, resulting in a substantial morbidity and mortality.\u003csup\u003e35\u0026ndash;37\u003c/sup\u003e In this study, it could be observed that coagulation dysfunction including fibrinolytic hyperfunction and DIC has a higher occurrence in the death group. Accordingly, prolonged APTT and PT, alteration of fibrinogen and decreased platelets levels are both correlated with poor in-hospital prognosis through machine learning.\u003c/p\u003e \u003cp\u003eA key innovation of our study is the application of machine learning techniques to identify mortality predictors in COVID-19 patients. This approach not only contributes to the existing body of knowledge but also offers a practical tool for healthcare practitioners in emergency settings. Based on the above variables we found, a user-friendly GUI is established, which requires further clinical validation. The GUI developed as part of this study serves as a user-friendly platform for rapidly assessing patient risk, aiding in timely and informed decision-making. The current development of wearable systems makes continuous and predictive monitoring possible. However, in a clinical setting, the monitoring of patients still relies on intermittent observations of vital signs combined with the use of EWS. The objective of this study was to develop an approach for real-time outcome prediction based on continuous vital signs monitoring and advanced machine learning techniques.\u003c/p\u003e \u003cp\u003eThe potential limitations of this study merit consideration. First, the data is confined to a single institution and a specific post-lockdown period, which may affect the generalizability of the findings. Future research should focus on replicated this study in various locations and for extended periods to validate and enhance the predictive model. Second, the omission of certain prognostic indicators like IL-6 and Lac due to excessive missing data may impact the study's comprehensiveness. Third, the sample size for both constructing and validating the risk score is small, and the data being exclusively from China could limit its applicability globally. The model's reliability and applicability across diverse populations requires further validation studies, especially from outside China.\u003c/p\u003e \u003cp\u003eIn summary, this study provides valuable insights into the increased emergency department visits at a top teaching hospital in China following the COVID-19 lockdown. The importance of machine learning in healthcare is underlined, especially through the creation of a predictive model with a graphical user interface. By using initial hospital admission data, this innovation aids in accurately assessing the risk of critically ill patients. These advancements are essential for improving treatment decisions and efficiently allocating medical resources in emergency care, which can help solve ongoing healthcare challenges.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study was funded by the Key Technologies Research and Development Program (grant numbers 2022YFE0131700, 2022YFC3602000) and the National Natural Science Foundation of China (grant numbers 82071813, 82271835). These funding sources supported all phases of this research, including design, collection, analysis, and interpretation of data.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthor information\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthors and Affiliations\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e1.\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Department of Emergency, Peking University People’s Hospital, Beijing, China\u003c/p\u003e\n\u003cp\u003e2.\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;School of biomedical sciences and engineering, South China University of Technology, Guangzhou, China\u003c/p\u003e\n\u003cp\u003e3.\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Department of Rheumatology and Immunology, Peking University People's Hospital, Beijing, China\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eContributions\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eYuanyuan Pei, Xi Wang, Jing He and Jihong Zhu contributed to the concept and design of this work. Lingjie Cao, Dilu Li, Liping Guo, Fengtao Yang and Wenfeng Huang participated in clinical data entry. Xi Wang was responsible for the statistical data analysis and machine learning. Hao Li and Yuanyuan Pei provides guidance on clinical data analysis methods. Yuanyuan Pei and Xi Wang was responsible for the article writing. All authors have read and approved the final manuscript and agree to be accountable for all aspects of the work.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCorresponding author\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eCorrespondence to ; Jing Heand Jihong Zhu\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthics Approval and Consent to Participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAll procedures performed in this study involving human participants were in accordance with the ethical standards of the institutional research committee and with the 1964 Helsinki declaration and its later amendments. This study was approved by the hospital ethics committee (reference No. 2023PHB217-001).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eInformed Consent\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eInformed consent was obtained from all patients or their family members included in the study.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for Publication\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eN/A.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAvailability of data and materials\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe datasets used or analyzed in this study are available from the corresponding author upon reasonable request.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eDeclaration of interests\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors declare that they have no conflicts of interest.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eWorld Health Organization. Available from: https://www.who.int/news-room/fact-sheets/detail/ coronavirus-disease- (covid-19). [Accessed 30th January 2024]\u003c/li\u003e\n\u003cli\u003eCrook H, Raza S, Nowell J, Young M, Edison P. Long covid-mechanisms, risk factors, and management. \u003cem\u003eBMJ\u003c/em\u003e. 2021;\u003cstrong\u003e374\u003c/strong\u003e:n1648. https://doi.org/10.1136/bmj.n1648\u003c/li\u003e\n\u003cli\u003eChen T, Wu D, Chen H, et al. Clinical characteristics of 113 deceased patients with coronavirus disease 2019: retrospective study. \u003cem\u003eBMJ\u003c/em\u003e. 2020;\u003cstrong\u003e368\u003c/strong\u003e:m1091.https://doi.org/10.1136/bmj.m1091 \u003c/li\u003e\n\u003cli\u003eGe J. The COVID-19 pandemic in China: from dynamic zero-COVID to current policy. \u003cem\u003eHerz\u003c/em\u003e. 2023;\u003cstrong\u003e48\u003c/strong\u003e(3):226-228. https://doi.org/10.1007/s00059-023-05183-5\u003c/li\u003e\n\u003cli\u003eBurki T. Dynamic zero COVID policy in the fight against COVID. \u003cem\u003eLancet Respir Med\u003c/em\u003e. 2022;\u003cstrong\u003e10\u003c/strong\u003e(6):e58-e59. https://doi.org/10.1016/S2213-2600(22)00142-4\u003c/li\u003e\n\u003cli\u003eBai W, Sha S, Cheung T, et al. Optimizing the dynamic zero-COVID policy in China. \u003cem\u003eInt J Biol Sci\u003c/em\u003e. 2022;\u003cstrong\u003e18\u003c/strong\u003e(14):5314-5316.https://doi.org/10.7150/ijbs.75699\u003c/li\u003e\n\u003cli\u003eFaust JS, Du C, Liang C, et al. Excess mortality in Massachusetts during the Delta and Omicron waves of COVID-19. \u003cem\u003eJAMA\u003c/em\u003e. 2022;\u003cstrong\u003e328\u003c/strong\u003e(1):74-76. https://doi.org/10.1001/jama.2022.8045\u003c/li\u003e\n\u003cli\u003eMarquez C, Kerkhoff AD, Schrom J, et al. COVID-19 symptoms and duration of rapid antigen test positivity at a community testing and surveillance site during pre-Delta, Delta, and Omicron BA.1 Periods. \u003cem\u003eJAMA Netw Open\u003c/em\u003e. 2022;\u003cstrong\u003e5\u003c/strong\u003e(10):e2235844. https://doi.org/10.1001/jamanetworkopen.2022.35844\u003c/li\u003e\n\u003cli\u003eCai J, Deng X, Yang J, et al. Modeling transmission of SARS-CoV-2 Omicron in China. \u003cem\u003eNat Med\u003c/em\u003e. 2022;\u003cstrong\u003e28\u003c/strong\u003e(7):1468-1475. https://doi.org/10.1038/s41591-022-01855-7\u003c/li\u003e\n\u003cli\u003eShortliffe EH, Sep\u0026uacute;lveda MJ. Clinical decision support in the era of artificial intelligence. \u003cem\u003eJAMA\u003c/em\u003e. 2018;\u003cstrong\u003e320\u003c/strong\u003e:2199-2200. https://doi.org/10.1001/jama.2018.17163\u003c/li\u003e\n\u003cli\u003eStead WW. Clinical implications and challenges of artificial intelligence and deep learning. \u003cem\u003eJAMA\u003c/em\u003e. 2018;\u003cstrong\u003e320\u003c/strong\u003e:1107-1108. https://doi.org/10.1001/jama.2018.11029\u003c/li\u003e\n\u003cli\u003eVaishya R, Javaid M, Khan IH, Haleem A. Artificial Intelligence (AI) applications for COVID-19 pandemic. \u003cem\u003eDiabetes Metab Syndr Clin Res Rev\u003c/em\u003e. 2020;\u003cstrong\u003e14\u003c/strong\u003e:337-339. https://doi.org/10.1016/j.dsx.2020.04.012\u003c/li\u003e\n\u003cli\u003eComito C, Pizzuti C. Artificial intelligence for forecasting and diagnosing COVID-19 pandemic: A focused review. \u003cem\u003eArtif Intell Med\u003c/em\u003e. 2022;\u003cstrong\u003e128\u003c/strong\u003e:102286.https://doi.org/10.1016/j.artmed.2022.102286\u003c/li\u003e\n\u003cli\u003eTheodosiou AA, Read RC. Artificial intelligence, machine learning and deep learning: Potential resources for the infection clinician. \u003cem\u003eJ Infect\u003c/em\u003e. 2023;\u003cstrong\u003e87\u003c/strong\u003e(4):287-294.https://doi.org/10.1016/j.jinf.2023.07.006\u003c/li\u003e\n\u003cli\u003eMagn\u0026uacute;sd\u0026oacute;ttir I, Lovik A, Unnarsd\u0026oacute;ttir AB, et al. Acute COVID-19 severity and mental health morbidity trajectories in patient populations of six nations: an observational study. \u003cem\u003eLancet Public Health\u003c/em\u003e. 2022;\u003cstrong\u003e7\u003c/strong\u003e(5):e406-e416.https://doi.org/10.1016/S2468-2667(22)00042-1 \u003c/li\u003e\n\u003cli\u003eJadhav S, Deng G, Zawin M, Kaufman AE. COVID-view: Diagnosis of COVID-19 using chest CT. \u003cem\u003eIEEE Trans Vis Comput Graph\u003c/em\u003e. 2022;\u003cstrong\u003e28\u003c/strong\u003e(1):227-237.https://doi.org/10.1109/TVCG.2021.3114851\u003c/li\u003e\n\u003cli\u003eGorman EA, O\u0026apos;Kane CM, McAuley DF. Acute respiratory distress syndrome in adults: diagnosis, outcomes, long-term sequelae, and management. \u003cem\u003eLancet\u003c/em\u003e. 2022; \u003cstrong\u003e400\u003c/strong\u003e(10358):1157-1170. https://doi.org/10.1016/S0140-6736(22)01439-8\u003c/li\u003e\n\u003cli\u003eKellum JA, Lameire N, Aspelin P, et al. Kidney disease: Improving global outcomes (KDIGO) acute kidney injury work group. KDIGO clinical practice guideline for acute kidney injury. \u003cem\u003eKidney Int Suppl\u003c/em\u003e. 2012;\u003cstrong\u003e2\u003c/strong\u003e:1-138. https://kdigo.org/wp-content/uploads/2016/10/KDIGO-2012-AKI-Guideline-English.pdf \u003c/li\u003e\n\u003cli\u003eKidney Disease: Improving Global Outcomes (KDIGO) CKD Work Group. KDIGO 2012 clinical practice guideline for the evaluation and management of chronic kidney disease.\u003cem\u003e Kidney Int Suppl.\u003c/em\u003e 2013;\u003cstrong\u003e3\u003c/strong\u003e(1):1-150. https://kdigo.org/wp-content/uploads/2017/02/KDIGO_2012_CKD_GL.pdf \u003c/li\u003e\n\u003cli\u003eIba T, Levy JH. Sepsis-induced coagulopathy and disseminated intravascular coagulation. \u003cem\u003eAnesthesiology.\u003c/em\u003e 2020;\u003cstrong\u003e132\u003c/strong\u003e(5):1238-1245. https://doi.org/10.1097/ALN.0000000000003122\u003c/li\u003e\n\u003cli\u003eFeng Y, Shao H, Gong X, et al. Share \u0026apos;Dynamic zero-COVID\u0026apos; policy and viral clearance during an omicron wave in Tianjin, China: a city-wide retrospective observational study. \u003cem\u003eBMJ Open\u003c/em\u003e. 2022;\u003cstrong\u003e12\u003c/strong\u003e(12):e066359. https://doi.org/10.1136/bmjopen-2022-066359\u003c/li\u003e\n\u003cli\u003eWalton M, Murray E, Christian MD. Mental health care for medical staff and affiliated healthcare workers during the COVID-19 pandemic. \u003cem\u003eEur Heart J Acute Cardiovasc Care\u003c/em\u003e. 2020;\u003cstrong\u003e9\u003c/strong\u003e(3):241-247. https://doi.org/10.1177/2048872620922795\u003c/li\u003e\n\u003cli\u003eCheng Z, Tao Y, Liu T, et al. Psychology, stress, insomnia, and resilience of medical staff in China during the COVID-19 policy opening: a cross-sectional survey. \u003cem\u003eFront Public Health\u003c/em\u003e. 2023;\u003cstrong\u003e11\u003c/strong\u003e:1249255. https://doi.org/10.3389/fpubh.2023.1249255\u003c/li\u003e\n\u003cli\u003eJamshidi E, Asgary A, Tavakoli N, et al. Using machine learning to predict mortality for COVID-19 patients on day 0 in the ICU. \u003cem\u003eFront Digit Health\u003c/em\u003e. 2022;\u003cstrong\u003e3\u003c/strong\u003e:681608. https://doi.org/10.3389/fdgth.2021.681608\u003c/li\u003e\n\u003cli\u003eHartzband P, Groopman J. Physician burnout, interrupted. \u003cem\u003eN Engl J Med.\u003c/em\u003e 2020;\u003cstrong\u003e382\u003c/strong\u003e:2485-2487. https://www.nejm.org/doi/full/10.1056/NEJMp2003149\u003c/li\u003e\n\u003cli\u003eLiang W, Liang H, Ou L, et al. Development and validation of a clinical risk score to predict the occurrence of critical illness in hospitalized patients with COVID-19. \u003cem\u003eJAMA Intern Med\u003c/em\u003e. 2020;\u003cstrong\u003e180\u003c/strong\u003e(8):1081-1089. https://doi.org/10.1001/jamainternmed.2020.2033 \u003c/li\u003e\n\u003cli\u003eZhang JJ, Dong X, Liu GH, Gao YD. Risk and protective factors for COVID-19 morbidity, severity, and mortality. \u003cem\u003eClin Rev Allergy Immunol\u003c/em\u003e. 2023;\u003cstrong\u003e64\u003c/strong\u003e(1):90-107.https://doi.org/10.1007/s12016-022-08921-5\u003c/li\u003e\n\u003cli\u003eGrasselli G, Greco M, Zanella A, et al. Risk factors associated with mortality among patients with COVID-19 in intensive care units in Lombardy, Italy. \u003cem\u003eJAMA Intern Med\u003c/em\u003e. 2020;\u003cstrong\u003e180\u003c/strong\u003e(10):1345-1355. https://doi.org/10.1001/jamainternmed.2020.3539\u003c/li\u003e\n\u003cli\u003eButkiewicz S, Zaczyński A, Hampel M, Pańkowski I, Gałązkowski R, Rzońca P. Analysis of risk factors for in-hospital death due to COVID-19 in patients hospitalised at the temporary hospital located at the national stadium in Warsaw: A retrospective analysis. \u003cem\u003eInt J Environ Res Public Health\u003c/em\u003e. 2022;\u003cstrong\u003e19\u003c/strong\u003e(7):3932. https://doi.org/10.3390/ijerph19073932\u003c/li\u003e\n\u003cli\u003eWang Y, Perlman S. COVID-19: Inflammatory profile. \u003cem\u003eAnnu Rev Med\u003c/em\u003e. 2022;\u003cstrong\u003e73\u003c/strong\u003e:65-80. https://doi.org/10.1146/annurev-med-042220-012417\u003c/li\u003e\n\u003cli\u003eYe Q, Wang B, Mao J. The pathogenesis and treatment of the \u0026lsquo;Cytokine Storm\u0026rsquo; in COVID-19.\u003cem\u003e J Infect\u003c/em\u003e. 2020;\u003cstrong\u003e80\u003c/strong\u003e(6):607-613. https://doi.org/10.1016/j.jinf.2020.03.037\u003c/li\u003e\n\u003cli\u003eMeng M, Chen L, Zhang S, et al. Risk factors for secondary hemophagocytic lymphohistiocytosis in severe coronavirus disease 2019 adult patients. \u003cem\u003eBMC Infect Dis\u003c/em\u003e. 2021;\u003cstrong\u003e21\u003c/strong\u003e(1):398. https://doi.org/10.1186/s12879-021-06094-8 \u003c/li\u003e\n\u003cli\u003eBivona G, Agnello L, Ciaccio M. Biomarkers for prognosis and treatment response in COVID-19 patients. \u003cem\u003eAnn Lab Med\u003c/em\u003e. 2021;\u003cstrong\u003e41\u003c/strong\u003e(6):540-548. https://doi.org/10.3343/alm.2021.41.6.540\u003c/li\u003e\n\u003cli\u003eSun J, Zheng Q, Madhira V, et al. Association between immune dysfunction and COVID-19 breakthrough infection after SARS-CoV-2 vaccination in the US. \u003cem\u003eJAMA Intern Med\u003c/em\u003e, 2022;\u003cstrong\u003e182\u003c/strong\u003e(2):153-162. https://doi.org/10.1001/jamainternmed.2021.7024 \u003c/li\u003e\n\u003cli\u003eHadid T, Kafri Z, Al-Katib A. Coagulation and anticoagulation in COVID-19. \u003cem\u003eBlood Rev\u003c/em\u003e. 2021;\u003cstrong\u003e47\u003c/strong\u003e:100761. https://doi.org/10.1016/j.blre.2020.100761\u003c/li\u003e\n\u003cli\u003eAsakura H, Ogawa H. COVID-19-associated coagulopathy and disseminated intravascular coagulation.\u003cem\u003e Int J Hematol\u003c/em\u003e. 2021;\u003cstrong\u003e113\u003c/strong\u003e(1):45-57. https://doi.org/10.1007/s12185-020-03029-y\u003c/li\u003e\n\u003cli\u003eConway EM, Mackman N, Warren RQ, et al. Understanding COVID-19-associated coagulopathy. \u003cem\u003eNat Rev Immunol\u003c/em\u003e. 2022;\u003cstrong\u003e22\u003c/strong\u003e(10):639-649. https://doi.org/10.1038/s41577-022-00762-9\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"COVID-19, Post-COVID-19 lockdown, Emergency department, Machine learning, Prognostic predictors","lastPublishedDoi":"10.21203/rs.3.rs-4326543/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4326543/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eCoronavirus disease of 2019 (COVID-19) has caused a global pandemic. Emergency department (ED) suffered a significant impact due to COVID-19 spread after policy adjustments at the end of 2022 in China.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eThis study analyzed the impact of post-COVID-19 lock-down on ED visits and critically ill patients at Peking University People's Hospital from December 2022 to January 2023. Machine learning was employed to identify key predictors of mortality in critically ill ED patients. A Graphical User Interface (GUI) was developed to estimate the prognostic predictors.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eWe have observed a significant rise in ED visits and admissions of critical patient, particularly with COVID-19 pneumonia. A total of 25413 patients visited ED, of who 631 patients were critically ill. Our analysis of 581 critical patients revealed distinct clinical and demographic characteristics like hypertension and diabetes, with a notable prevalence of complications such as acute respiratory distress syndrome, acute kidney injury and respiratory failure. We further studied the variables with high contribution to model prediction to observe the characteristic differences between the variables in the non-survival group and the survival group. Age, hypoxic state and ventilator support, white blood cell, platelets, and coagulation indicators were identified as key risk factors for mortality using a Random Forest model. The study's predictive model demonstrated high accuracy, with its area under the receiver-operator curve as 0\u0026middot;8385, which incorporated into a user-friendly GUI for clinical application and could enhance the management of critical COVID-19 cases in emergency settings.\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e \u003cp\u003eThe pandemic spread rapidly in China after the quarantine was lifted. The predictive score and GUI for estimating prognostic risk factors in ED critical patients can be used to aid in the proper treatment and optimizing medical resources.\u003c/p\u003e","manuscriptTitle":"Impact analysis and predictive modeling in emergency care： Evaluating the effects of immediately post-COVID-19 lockdown at a top Chinese teaching hospital","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-06-04 15:15:28","doi":"10.21203/rs.3.rs-4326543/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"abe765c7-2cab-499f-8177-b81aa2e8e162","owner":[],"postedDate":"June 4th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-08-08T07:37:35+00:00","versionOfRecord":[],"versionCreatedAt":"2024-06-04 15:15:28","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4326543","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4326543","identity":"rs-4326543","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}