Development and validation of a clinical prediction model for in-hospital mortality of severe pneumonia based on machine learning

Development and validation of a clinical prediction model for in-hospital mortality of severe pneumonia based on machine learning | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article Development and validation of a clinical prediction model for in-hospital mortality of severe pneumonia based on machine learning Kai Xie, Xiajin Huang, Zhen Li, Wenjing Yin, Xiaoxuan He, Xinyu Miao, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5685118/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Objective: We aimed to develop an interpretable model to predict the mortality risk for patients with severe pneumonia. Methods: The study retrospectively employed data from severe pneumonia patients hospitalized at the First Affiliated Hospital of Henan University of Chinese Medicine and Henan Provincial Hospital of Chinese Medicine between January 2008 and November 2021 as the training set for the model development. Patients with severe pneumonia admitted from the same two hospitals between December 2021 and January 2024 were prospectively included as the test set for the model evaluation. The demographic characteristics, clinical manifestations upon admission, risk factors upon admission, comorbidities, complications, laboratory results, treatment during hospitalization, other features, and fatal outcomes were collected. In the training set, all data were analyzed in comparison to survivors and non-survivors. The least absolute shrinkage and selection operator (LASSO) regression was applied to select features for the establishment of five models: logistic regression (LR), support vector machine (SVM), decision tree (DT), random forest (RF), and extreme gradient boosting (XGBoost). The performance of the models was assessed from discrimination, calibration and clinical practicability. The optimal model was screened out, and SHapley Additive exPlanation (SHAP) method was used to explain. Results: A total of 323 eligible patients with severe pneumonia were enrolled, including 226 patients in the training set and 97 in the test set. In comparison to the other four models, the XGBoost model demonstrated the third highest AUROC (0.853), along with optimal calibration and clinical practicability. The SHAP value of the XGBoost model indicated that the retention catheterization applicationhad the strongest predictive value for all prediction horizons, closely followed by the variables of oral Chinese herbal decoction, BUN level, age, tracheotomy application, complication of septic shock, and TCM syndrome (pathogenic qi falling into and prostration syndrome). Conclusions: Older age, increased BNU level, complication of septic shock, tracheotomy application, retention catheterization application, oral Chinese herbal decoction, and TCM syndrome (pathogenic qi falling into and prostration syndrome) may be potential risk factors that affect mortality in severe pneumonia, among which tracheotomy application and oral Chinese herbal decoction are protective factors. The XGBoost model exhibits superior overall performance in predicting hospital mortality risk for severe pneumonia, greater than traditional scoring systems such as PSI, SOFA, and APACHE II, which assists clinicians in prognostic assessment, resulting in improved therapeutic strategies and optimal resource allocation for patients. Health sciences/Diseases/Respiratory tract diseases Health sciences/Diseases Health sciences/Risk factors Severe pneumonia Machine learning Prediction model Mortality Traditional Chinese medicine Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Introduction The 2019 Global Burden of Disease Study indicated that lower respiratory infections ranked as the fourth major cause of global mortality, resulting in over 2.49 million deaths, beaten only by newborn illnesses, ischemic heart disease, and stroke 1 . Severe pneumonia is a frequently occurring life-threatening disease characterized by lower respiratory infection, with a high mortality, numerous complications, a poor prognosis, and a significant economic burden 2 . Furthermore, it is a primary cause of ICU hospitalization and infection-related death around the world 3 . In the United States, pneumonia causes 78% of infection-related deaths 4 . Despite continuous breakthroughs in therapy over the last few decades, severe pneumonia has always been linked with a significant death rate, ranging from 20% to more than 50% 5 . Thus, the identification of early hospital mortality risk in patients with severe pneumonia is essential and may facilitate appropriate care and clinical decision support. In recent years, identifying mortality risk factors in patients with severe pneumonia has emerged as the main study focus. Researchers have discovered several factors associated with mortality in patients with severe pneumonia, including high mean platelet volume levels 5 , increased admission lactate 6 , C-reactive protein (CRP)-to-albumin ratio 7 , admission interleukin (IL)-32 concentration 8 , the Modified Nutrition Risk in Critically ill (mNUTRIC) score 9 , elevated stress hyperglycemia ratio 10 , serum Krebs von den Lungen-6 11 , the ratio of total body water to fat-free mass 12 , thrombocytopenia 13 , severe thinness (Body Mass Index <16 kg/m 2 ) 14 , and the presence of septic shock 15 . Nevertheless, these factors are comparatively singular and varied. Despite a systematic review that comprehensively analyze existing literature to identify mortality risk factors for severe pneumonia 16 , there is an absence of precise prediction applicable to individual cases. The clinical prediction model can estimate the probability of a specific individual currently suffering from a certain condition or experiencing a certain outcome in the future by assigning relative weights to each predictor variable and combining multiple predictor variables 17 . There has been an increasing number of studies on prediction models worldwide. However, there is an absence of predictive models regarding the mortality risk associated with severe pneumonia that contain traditional Chinese medicine (TCM) characteristics, as well as inadequate comparisons among existing models; moreover, selection and consideration of predictive variables are insufficient. Hence, it is crucial to develop a comprehensive and systematic mortality risk prediction model for severe pneumonia containing TCM characteristics. Based on clinical needs, constructing prediction models can greatly promote the implementation of precision medicine, support thorough clinical diagnosis and evidence-based decision-making, and optimize public health resources allocation. The advancement of electronic medical record systems has helped in the availability of substantial clinical data. Nonetheless, conventional logistic regression is incapable of managing complex clinical data 18 . Currently, artificial intelligence (AI) technology has achieved substantial breakthroughs, introducing novel techniques for data processing and extraction. Machine learning, a core component of AI, can autonomously develop data models, recognize complex data patterns, and predict results based on insights derived from computer algorithms 19 . Due to the inherent capabilities of machine learning algorithms, an increasing number of researchers support the implementation of novel predictive models based on machine learning to facilitate suitable diagnosis and treatment, compared to conventional illness severity classification systems like the Sequential Organ Failure Assessment (SOFA) score or the Acute Physiology and Chronic Health Evaluation (APACHE) II score 20 . Normal supervised machine learning classifiers possess distinct characteristics, and their performance is frequently dependent upon the attributes of the datasets being classified. Logistic regression (LR), support vector machine (SVM), decision tree (DT), random forest (RF), and extreme gradient boosting (XGBoost) are popular machine learning techniques; yet, their specific performance on severe pneumonia datasets remains ambiguous. Therefore, this study aimed to accurately, quickly, and comprehensively predict the individual mortality risk of patients with severe pneumonia and improve prognosis by establishing a mortality risk prediction model for severe pneumonia containing the characteristics of TCM using multiple machine learning algorithms. Methods Study design and population This study was conducted to develop a model to predict hospital mortality in patients with severe pneumonia. A retrospective observational study in training set was designed to consecutively enroll patients in wards at the First Affiliated Hospital of Henan University of Chinese Medicine and Henan Provincial Hospital of Chinese Medicine from January 2008 to November 2021. The test set was consistent with patient source for the training set, but prospectively observational study from December 2021 to January 2024. The follow-up of all participants continued until discharge or death. This study was approved by the Ethics Committee of the First Affiliated Hospital of Henan University of Chinese Medicine (No. 2023HL-241-01). All patients or their legal guardians in the test set were asked to sign an informed consent form. However, due to the retrospective nature for the training set, the need to obtain the informed consent was waived by the the Ethics Committee of the First Affiliated Hospital of Henan University of Chinese Medicine. This study complied with the principles defined in the Declaration of Helsinki and the International Conference on Harmonization-Good Clinical Practice guidelines. Inclusion and exclusion criteria The inclusion criteria for the training set were: (1) Participants must have a diagnosis of severe pneumonia in accordance with the guidelines established by the Respiratory Society of the Chinese Medical Association 21 or the Infectious Disease Society of America/American Thoracic Society 22 ; (2) The diagnosis of TCM syndrome must adhere to the Traditional Chinese Medicine Diagnosis and Treatment Guidelines for Community-Acquired Pneumonia (2018 Revised Edition) published by the Chinese Medical Association 23 ; (3) There were no restrictions regarding the gender or comorbidities of the patients, except they had to be 18 years of age or older. The exclusion criteria were: (1) Numerous missing clinical data; (2) A hospital stay of fewer than 3 days. The inclusion criteria for the test set were: (1) Participants must be diagnosed with severe pneumonia in accordance with the guidelines of the Respiratory Society of the Chinese Medical Association 21 or the Infectious Disease Society of America/American Thoracic Society 22 and recruited within three days; (2) There were no restrictions regarding gender or comorbidities, provided participants were 18 years or older; (3) All patients, or their legal representatives in cases where they were unable to provide consent, were required to sign an informed consent form. Besides, individuals with dementia and other mental disorders were excluded. We excluded patients with clearly diagnosed fungal and viral pneumonia, including severe Influenza A (H1N1), severe acute respiratory syndrome (SARS), or coronavirus disease 2019 (COVID-19) from both the training and test sets to improve homogeneity. Outcome definition The prediction outcome of this study was the probability of in-hospital mortality, defined as deaths during the current hospitalization period, including within one day after discharge. Features extraction Demographic characteristics, clinical manifestations, admission risk factors, comorbidities, complications, laboratory results, treatment during hospitalization, and other variables, totaling 115, were as candidates that affect mortality in severe pneumonia. Details were presented in Table 1 . Table 1 The detailed features of collection Item Feature Demographic characteristics age, gender, nationality, and solar term Clinical manifestations upon admission body temperature, respiratory rate, heart rate, systolic and diastolic blood pressure Risk factors upon admission history of allergies, smoking, alcohol consumption, fracture, surgery, long-term bed rest, hospitalization within 90 days, ICU admission within 90 days, intravenous antibiotics within 30 days, dialysis within 30 days Comorbidities hypertension, diabetes, chronic bronchitis, chronic obstructive pulmonary disease (COPD), pulmonary fibrosis, bronchiectasis, asthma, old pulmonary tuberculosis, pulmonary abscess, pulmonary heart disease, arrhythmia, cardiac insufficiency, chronic heart failure, parkinson’s disease, cerebral infarction, hematencephalon, chronic gastritis, gastrointestinal bleeding, chronic viral hepatitis, liver cirrhosis, chronic renal insufficiency, chronic renal failure, cancer, lumbar disease, and neck disease Complications acid base disturbance, electrolyte imbalance, anemia, hypoproteinemia, acute heart failure, acute myocardial infarction, acute kidney injury, acute liver injury, hypovolemic shock, septic shock, cardiac shock, and pleural effusion Laboratory results white blood cell (WBC) count, red blood cell (RBC) count, hemoglobin, hematokrit, platelet count, neutrophilic granulocyte percentage (NEUT%), lymphocyte percentage (LY%), CRP, procalcitonin (PCT), total bilirubin, total protein, albumin, aspartate aminotransferase (AST), alanine amiotransferase (ALT), blood urea nitrogen (BUN), serum creatinine (Scr), potassium, sodium, troponin, myohemoglobin, prothrombin time (PT), activated partial thromboplastin time (APTT), fibrinogen, D-dimer, brain natriuretic peptide (BNP), arterial blood PH, arterial partial pressure of oxygen (PaO 2 ), arterial partial pressure of carbon dioxide (PaCO 2 ), and arterial oxygenation index (PaO 2 /FiO 2 ) Treatment during hospitalization conventional medicine glucocorticoids, number of antibiotics ≥ 3, beta-lactam antibiotics, quinolone antibiotics, aminoglycoside antibiotics, macrolide antibiotics, tetracycline antibiotics sulfonamide antibiotics, antifungal drug, immunosuppressant conventional operation fiber bronchoscope, transfusion, hemodialysis, extracorporeal membrane oxygenation (ECMO), tracheotomy, retention catheterization, gastric intubation, deep vein catheterization, days of nasal tube oxygen, mask oxygen days, non-invasive mechanical ventilation, invasive mechanical ventilation, and mechanical ventilation TCM or TCM appropriate technology oral Chinese herbal decoction, Chinese patent medicine injection, TCM appropriate technology Others TCM syndrome, multi-drug resistant bacterial infection, total hospitalization days, days of ICU stay Missing data handling Investigated and confirmed outliers and missing numbers in the original electronic medical records database. If verification or supplementation was not possible, consider the outlier as a missing value for processing. Variables with missing data over 25% were removed, while multiple imputation would be employed for those within 25%. Statistical analysis Every statistical analysis and calculations were employed SPSS 26.0 or R 4.3.2 software. The categorical variables expressed as total numbers and percentages, and the χ2 test or Fisher exact test (expected frequency < 10) was employed to compare group differences. The normality test was performed on all continuous variables to ascertain if the data adhered to a normal distribution, mostly using the Shapiro Wilk or Kolmogorov Smirnov tests in conjunction with histograms. If the data adhered to a normal distribution, represented as mean ( \(\:\stackrel{-}{x}\) ) ± standard deviation (SD), an t-test was employed to assess group differences; conversely, it was denoted by the median and interquartile range (IQR), and applied the Wilcoxon rank sum test. Features selection Patients with severe pneumonia were categorized into non-survivor and survivor groups based on in-hospital mortality, and characteristics were presented and compared between the groups. The 115 features collected from the training set underwent statistical analysis to identify variables with significant differences between the non-survivor and survivor groups. Additionally, to prevent overfitting, the Least Absolute Shrinkage and Selection Operator (LASSO) using the glmnet package in R 4.3.2 software was employed with 10-fold cross-validation to identify and refine candidate predictors 24 . The simplest subset of predictive factors was chosen to identify the independent features for inclusion in the in-hospital mortality risk prediction model for severe pneumonia. Model development and performance evaluation Five machine learning algorithms were employed to develop predictive models: LR, SVM, DT, RF, and XGBoost. The corresponding software packages utilized were glm, e1071, rpart, randomForest, and xgboost, all implemented in R version 4.3.2. The discrimination of each model was assessed using the area under the receiver operating characteristic curve (AUROC) and confusion matrix. Besides, DeLong test was used to compare AUC values and further evaluate the differences in predictive performance between models. The calibration curve assessed the calibration; furthermore, to test the clinical applicability for decision-making by estimating the net benefit at various threshold probabilities, decision curve analysis (DCA) was conducted 25 . Results Basic Features A total of 226 adult patients diagnosed with severe pneumonia were included into the final training set for this study, while 97 in the test set. The in-hospital mortality for severe pneumonia was 23.82% in the training set and 29.89% in the test set. No significant difference in mortality was seen between the training and test sets ( P > 0.05). Table 2 summarized the comparisons of demographic characteristics, clinical manifestations at admission, risk factors before admission, comorbidities, complications, laboratory results, treatment during hospitalization, and other factors between non-survivors and survivors in the training set. In the training set, there were significant statistical differences between the non-survivors and survivors in a total of 38 factors including age, TCM syndrome, risk factors before admission of fracture history, long-term bed rest history, and intravenous antibiotics within 30 days, comorbidities for cerebral infarction, cardiac insufficiency, gastrointestinal bleeding, and cancer, complications for electrolyte imbalance, anemia, hypoproteinemia, pleural effusion, and septic shock, laboratory results for hematokrit, NEUT%, PCT, total protein, albumin, BUN, Scr, troponin, myohemoglobin, fibrinogen, D-dimer, and arterial blood PH, as well as antifungal drug, transfusion, tracheotomy, retention catheterization, gastric intubation, deep vein catheterization, days of nasal tube oxygen, days of invasive mechanical ventilation, days of mechanical ventilation, oral Chinese herbal decoctions, TCM syndrome, total hospitalization days, days of ICU stay ( P < 0.05), which might be the potential risk factors for death in patients with severe pneumonia. The comparison of features between the training set and the test set was presented in Table 3 . The training set mainly occurred during the Lesser Cold, Greater Cold, Grain in Beard, and Winter Solstice solar periods, whereas the test set was primarily linked with the Winter Solstice and Lesser Cold. The distribution between the two datasets was statistically significant ( P = 0.034). In the training set, the history of alcohol consumption, the presence of pleural effusion comorbidity, the use of three or more antibiotics, the frequency of quinolone antibiotics, as well as hematocrit, ALT, and D-dimer levels, and the duration of mask oxygen therapy were all significantly raised compared to the test set ( P < 0.05). The comorbidity of gastrointestinal bleeding and the levels of PCT, myohemoglobin, and PaO 2 were considerably reduced compared to the test set ( P 0.05). Table 2 Features comparison between the non-survivors and the survivors for severe pneumonia patients in the training set Feature Non-survivors ( n = 64) Survivors ( n = 162) P value Age 78.5 (69.25–85.75) 70.5 (58.75–79.25) < 0.001* Male 44 (68.75%) 114 (70.37%) 0.938 Nationalitiy 1.000 Han 64 (100.00%) 160 (98.77%) others 0 (0.00%) 2 (1.23%) Solar term 0.319 Lesser Cold 2 (3.13%) 14 (8.64%) Greater Cold 2 (3.13%) 14 (8.64%) the Beginning of Spring 2 (3.13%) 7 (4.32%) Rain Water 2 (3.13%) 8 (4.94%) Insects awaken 3 (4.69%) 6 (3.70%) the Spring Equinox 2 (3.13%) 4 (2.47%) Pure Brightness 1 (1.56%) 6 (3.70%) Grain Rain 3 (4.69%) 7 (4.32%) the Beginning of Summer 1 (1.56%) 6 (3.70%) Lesser Fullness of Grain 1 (1.56%) 4 (2.47%) Grain in Beard 6 (9.38%) 10 (6.17%) the Summer Solstice 3 (4.69%) 3 (1.85%) Lesser Heat 2 (3.13%) 9 (5.56%) Greater Heat 3 (4.69%) 8 (4.94%) the Beginning of Autumn 3 (4.69%) 3 (1.85%) the End of Heat 2 (3.13%) 5 (3.09%) White Dew 0 (0.00%) 5 (3.09%) the Autumn Equinox 7 (10.94%) 4 (2.47%) Cold Dew 2 (3.13%) 6 (3.70%) Frost’s Descent 2 (3.13%) 6 (3.70%) the Beginning of Winter 4 (6.25%) 7 (4.32%) Lesser Snow 0 (0.00%) 7 (4.32%) Greater Snow 4 (6.25%) 6 (3.70%) the Winter Solstice 7 (10.94%) 7 (4.32%) Vital signs Body temperature (℃) 37.05 (36.5–38) 36.9 (36.5–38.3) 0.903 Respiratory rate (breaths/min) 22.5 (20–30) 21 (20–25) 0.301 Heart rate (beats/min) 100.5 (84.25-116.75) 95.5 (80–112) 0.385 Systolic pressure (mmHg) 126 (108.5-145.75) 126 (116–140) 0.779 Diastolic pressure (mmHg) 76 (65–84) 77 (70–84) 0.363 Risk factors before admission Allergic history 8 (12.50%) 19 (11.73%) 1.000 Smoking history 10 (15.63%) 36 (22.22%) 0.281 Alcohol consumption history 7 (10.94%) 28 (17.28%) 0.308 Fracture history 12 (18.75%) 13 (8.02%) 0.032* Surgery history 28 (43.75%) 55 (33.95%) 0.220 Long-term bed rest history 35 (54.69%) 62 (38.27%) 0.026* Hospitalization within 90 days 38 (59.38%) 99 (61.11%) 0.880 ICU admission within 90 days 7 (10.94%) 34 (20.99%) 0.087 Intravenous antibiotics within 30 days 23 (35.94%) 89 (54.94%) 0.010* Dialysis within 30 days 0 (0.00%) 7 (4.32%) 0.207 Comorbidities Hypertension 36 (56.25%) 81 (50.00%) 0.461 Diabetes 20 (31.25%) 48 (29.63%) 0.872 Chronic bronchitis 10 (15.63%) 18 (11.11%) 0.374 COPD 12 (18.75%) 21 (12.96%) 0.298 Pulmonary fibrosis 8 (12.50%) 19 (11.73%) 1.000 Bronchiectasis 1 (1.56%) 6 (3.70%) 0.681 Asthma 1 (1.56%) 9 (5.56%) 0.339 Old pulmonary tuberculosis 1 (1.56%) 8 (4.94%) 0.428 Pulmonary abscess 0 (0.00%) 2 (1.23%) 1.000 Pulmonary heart disease 2 (3.12%) 8 (4.94%) 0.812 Arrhythmia 21 (32.81%) 33 (20.37%) 0.057 Cardiac insufficiency 12 (18.75%) 10 (6.17%) 0.006* Chronic heart failure 10 (15.63%) 13 (8.02%) 0.140 Parkinson’s disease 3 (4.69%) 7 (4.32%) 1.000 Cerebral infarction 35 (54.69%) 52 (32.10%) 0.002* Hematencephalon 8 (12.50%) 15 (9.26%) 0.626 Chronic gastritis 5 (7.81%) 7 (4.32%) 0.468 Gastrointestinal bleeding 6 (9.38%) 2 (1.23%) 0.010* Chronic viral hepatitis 2 (3.12%) 10 (6.17%) 0.554 Liver cirrhosis 1 (1.56%) 6 (3.70%) 0.681 Chronic renal insufficiency 4 (6.25%) 5 (3.09%) 0.473 Chronic renal failure 2 (3.12%) 6 (3.70%) 1.000 Cancer 9 (14.06%) 5 (3.09%) 0.005* Lumbar disease 6 (9.38%) 9 (5.56%) 0.458 Neck disease 2 (3.12%) 4 (2.47%) 1.000 Complications Acid base disturbance 36 (56.25%) 88 (54.32%) 0.882 Electrolyte imbalance 48 (75.00%) 97 (59.88%) 0.045* Anemia 46 (71.88%) 89 (54.94%) 0.024* Hypoproteinemia 59 (92.19%) 130 (80.25%) 0.029* Pleural effusion 62 (96.88%) 134 (82.72%) 0.005* Acute myocardial infarction 3 (4.69%) 4 (2.47%) 0.659 Acute heart failure 9 (14.06%) 10 (6.17%) 0.065 Acute kidney injury 12 (18.75%) 7 (4.32%) 0.389 Acute liver injury 7 (10.94%) 13 (8.02%) 0.603 Hypovolemic shock 2 (3.12%) 2 (1.23%) 0.681 Septic shock 18 (28.13%) 11 (6.79%) < 0.001* Cardiac shock 2 (3.12%) 4 (2.47%) 1.000 Laboratory results WBC (×10 9 /L) 9.85 (6.66–15.71) 8.6 (6.68–12.03) 0.187 RBC (×10¹²/L) 3.68 (3.1–4.32) 3.91 (3.41–4.43) 0.087 Hemoglobin (g/L) 111 (94.25–129.5) 119 (101.75-134.25) 0.061 Hematokrit (%) 33.9 (28.75–38.38) 36.6 (31.35–40.73) 0.021* Platelet count (×10 9 /L) 184.5 (112–236) 191 (134.75–249.5) 0.214 NEUT% 88.7 (82.95–93.2) 84.2 (76.28–89.83) 0.004* LY% 7.55 (3.87–12.38) 9.85 (5.93–15.1) 0.076 CRP (mg/L) 84.11 (35.5-161.91) 78.79 (30.92–161) 0.449 PCT (µg/L) 0.62 (0.36–2.95) 0.35 (0.1–0.77) < 0.001* Total bilirubin (µmol/L) 15.15 (9.93–24.43) 12.85 (9.3–18.9) 0.100 Total protein (g/L) 56.71 ± 11.19 60.44 ± 8.88 0.019* Albumin (g/L) 29.75 ± 6.3 32.19 ± 4.93 0.007* ALT (U/L) 22.05 (13.25–35.68) 22.1 (13.45–39.53) 0.920 AST (U/L) 30.25 (19.28–58.25) 26.25 (16.98–44.1) 0.281 BUN (mmol/L) 11.85 (7.4-17.52) 6.48 (4.63–10.38) < 0.001* Scr (µmol/L) 81.75 (56-134.58) 65.5 (50.15–94.7) 0.021* Potassium (mmol/L) 4.2 ± 0.76 4.15 ± 0.75 0.654 Sodium (mmol/L) 137.2 (132.1-141.78) 137.6 (134.88–141) 0.619 Troponin (ng/ml) 0.05 (0.05–0.19) 0.05 (0.01–0.07) < 0.001* Myohemoglobin (ng/ml) 40.74 (40.74-78) 40.74 (21.1-69.83) 0.022* PT (s) 13.75 (12.2-15.58) 12.95 (11.7-14.53) 0.051 APTT (s) 34.55 (29.3-40.25) 33.05 (28.48–39.28) 0.253 Fibrinogen (g/L) 4.62 (3.03–5.8) 5.37 (4.1–6.56) 0.013* D-dimer (µg/ml) 2.93 (1.79–5.06) 2.11 (1.02–3.79) 0.007* BNP (pg/ml) 190 (80.16-578.63) 245 (83.96–881.5) 0.392 Arterial blood PH 7.43 (7.36–7.46) 7.44 (7.42–7.48) 0.008* PaO 2 (mmHg) 61.4 (56-83.8) 61.4 (54-70.08) 0.174 PaCO 2 (mmHg) 32.95 (25.38–37.95) 32.95 (29.95–40.08) 0.196 PaO 2 /FiO 2 229.5 (171.75-261.75) 229.5 (193.75–276) 0.101 Application of conventional medicine Glucocorticoids 36 (56.25%) 91 (56.17%) 1.000 Number of antibiotics ≥ 3 54 (84.38%) 117 (72.22%) 0.055 Beta-lactam antibiotics 64 (100.00%) 158 (97.53%) 0.479 Quinolone antibiotics 41 (64.06%) 122 (75.31%) 0.101 Aminoglycoside antibiotics 9 (14.06%) 17 (10.49%) 0.490 Macrolide antibiotics 12 (18.75%) 25 (15.43%) 0.553 Tetracycline antibiotics 16 (25.00%) 24 (14.81%) 0.083 Sulfonamide antibiotics 0 (0.00%) 1 (0.62%) 1.000 Antifungal drug 27 (42.19%) 45 (27.78%) 0.041* Immunosuppressant 4 (6.25%) 5 (3.09%) 0.473 Conventional operation Fiber bronchoscope 31 (48.44%) 76 (46.91%) 0.883 Transfusion 21 (32.81%) 31 (19.14%) 0.035* Hemodialysis 4 (6.25%) 8 (4.94%) 0.947 ECMO 1 (1.56%) 1 (0.62%) 0.487 Tracheotomy 3 (4.69%) 30 (18.52%) 0.008* Retention catheterization 56 (87.50%) 73 (45.06%) < 0.001* Gastric intubation 45 (70.31%) 78 (48.15%) 0.003* Deep vein catheterization 39 (60.94%) 75 (46.30%) 0.047* Days of nasal tube oxygen 0 (0-8.5) 4 (0–14) 0.019* Days of mask oxygen days 0 (0–1) 0 (0–0) 0.095 Days of non-invasive mechanical ventilation 0 (0–3) 0 (0–2) 0.098 Days of invasive mechanical ventilation 1.5 (0–8) 0 (0–4) < 0.001* Days of mechanical ventilation 6.5 (1–11) 0 (0–11) 0.005* TCM or TCM appropriate technology Oral Chinese herbal decoction 27 (42.19%) 139 (85.80%) < 0.001* Chinese patent medicine injection 55 (85.94%) 126 (77.78%) 0.198 TCM appropriate technology 54 (84.38%) 136 (83.95%) 1.000 TCM syndrome < 0.001* Phlegm-heat obstructing lung syndrome 13 (20.31%) 65 (40.12%) Phlegm turbidity obstructing lung syndrome 17 (26.56%) 26 (16.05%) Deficiency of both qi and yin syndrome 9 (14.06%) 14 (8.64%) Lung-spleen qi deficiency syndrome 6 (9.38%) 10 (6.17%) Lung-spleen qi deficiency combined with phlegm turbidity obstructing lung syndrome 2 (3.13%) 11 (6.79%) Phlegm turbidity obstructing lung combined with stagnation of blood syndrome 2 (3.13%) 7 (4.32%) Deficiency of both qi and yin combined with phlegm turbidity obstructing lung syndrome 1 (1.56%) 7 (4.32%) Pathogenic qi falling into and prostration syndrome 6 (9.38%) 1 (0.62%) Invasion of pericardium by heat syndrome 0 (0.00%) 6 (3.70%) Phlegm-heat obstructing lung combined with stagnation of blood syndrome 1 (1.56%) 5 (3.09%) Deficiency of both qi and yin combined with phlegm-heat obstructing lung syndrome 2 (3.13%) 4 (2.47%) Lung-spleen qi deficiency combined with phlegm-heat obstructing lung syndrome 1 (1.56%) 4 (2.47%) Lung-spleen qi deficiency combined with stagnation of blood syndrome 2 (3.13%) 2 (1.23%) Stagnation of blood syndrome 1 (1.56%) 0 (0.00%) Deficiency of both qi and yin combined with stagnation of blood syndrome 1 (1.56%) 0 (0.00%) Others Multi-drug resistant bacterial infection 20 (31.25%) 49 (30.25%) 1.000 Total hospitalization days 12 (8.25-23) 17 (13–27) 0.001* Days of ICU stay 4 (0-10.5) 0 (0-4.25) < 0.001* Table 3 Features comparison between the training and test set Feature Training Set ( n = 226) Test Set ( n = 97) P value Age 72 (63–82) 76 (65–84) 0.155 Male 158 (69.91%) 60 (61.86%) 0.157 Nationalitiy 1.000 Han 224 (99.12%) 96 (98.97%) others 2 (0.88%) 1 (1.03%) Solar term 0.034* Lesser Cold 16 (7.08%) 11 (11.34%) Greater Cold 16 (7.08%) 3 (3.09%) the Beginning of Spring 9 (3.98%) 7 (7.22%) Rain Water 10 (4.42%) 4 (4.12%) Insects awaken 9 (3.98%) 1 (1.03%) the Spring Equinox 6 (2.65%) 7 (7.22%) Pure Brightness 7 (3.10%) 3 (3.09%) Grain Rain 10 (4.42%) 5 (5.15%) the Beginning of Summer 7 (3.10%) 6 (6.19%) Lesser Fullness of Grain 5 (2.21%) 5 (5.15%) Grain in Beard 16 (7.08%) 4 (4.12%) the Summer Solstice 6 (2.65%) 2 (2.06%) Lesser Heat 11 (4.87%) 2 (2.06%) Greater Heat 11 (4.87%) 2 (2.06%) the Beginning of Autumn 6 (2.65%) 4 (4.12%) the End of Heat 7 (3.10%) 7 (7.22%) White Dew 5 (2.21%) 1 (1.03%) the Autumn Equinox 11 (4.87%) 4 (4.12%) Cold Dew 8 (3.54%) 0 (0.00%) Frost’s Descent 8 (3.54%) 1 (1.03%) the Beginning of Winter 11 (4.87%) 0 (0.00%) Lesser Snow 7 (3.10%) 1 (1.03%) Greater Snow 10 (4.42%) 4 (4.12%) the Winter Solstice 14 (6.19%) 13 (13.40%) Vital signs Body temperature (℃) 36.9 (36.5-38.23) 36.8 (36.5–37.8) 0.226 Respiratory rate (breaths/min) 22 (20–27) 22 (20–26) 0.770 Heart rate (beats/min) 97.5 (80–113) 89 (80–107) 0.330 Systolic pressure (mmHg) 126 (114–140) 123 (113.5-135.5) 0.180 Diastolic pressure (mmHg) 76 (69–84) 75 (66–81) 0.224 Risk factors before admission Allergic history 27 (11.95%) 17 (17.53%) 0.180 Smoking history 46 (20.35%) 14 (14.43%) 0.210 Alcohol consumption history 35 (15.49%) 7 (7.22%) 0.043* Fracture history 25 (11.06%) 11 (11.34%) 0.942 Surgery history 83 (36.73%) 30 (30.9%) 0.317 Long-term bed rest history 97 (42.92%) 46 (47.42%) 0.455 Hospitalization within 90 days 137 (60.62%) 60 (61.86%) 0.835 ICU admission within 90 days 41 (18.14%) 17 (17.53%) 0.895 Intravenous antibiotics within 30 days 112 (49.56%) 58 (59.79%) 0.091 Dialysis within 30 days 7 (3.10%) 3 (3.09%) 1.000 Comorbidities Hypertension 117 (51.77%) 50 (51.55%) 0.971 Diabetes 68 (30.09%) 33 (34.02%) 0.971 Chronic bronchitis 28 (12.39%) 4 (4.12%) 0.023 COPD 33 (14.60%) 12 (12.37%) 0.596 Pulmonary fibrosis 27 (11.95%) 16 (16.49%) 0.270 Bronchiectasis 7 (3.10%) 3 (3.09%) 1.000 Asthma 10 (4.42%) 1 (1.03%) 1.000 Old pulmonary tuberculosis 9 (3.98%) 2 (2.06%) 0.591 Pulmonary abscess 2 (0.88%) 0 (0.00%) 1.000 Pulmonary heart disease 10 (4.42%) 1 (1.03%) 0.227 Arrhythmia 54 (23.89%) 33 (34.02%) 0.081 Cardiac insufficiency 22 (9.73%) 14 (14.43%) 0.219 Chronic heart failure 23 (10.18%) 14 (14.43%) 0.271 Parkinson’s disease 10 (4.42%) 4 (4.12%) 1.000 Cerebral infarction 87 (38.50%) 35 (36.08%) 0.682 Hematencephalon 23 (10.18%) 8 (8.25%) 0.589 Chronic gastritis 12 (5.31%) 3 (3.09%) 0.562 Gastrointestinal bleeding 8 (3.54%) 9 (9.28%) 0.034* Chronic viral hepatitis 12 (5.31%) 3 (3.09%) 0.562 Liver cirrhosis 7 (3.10%) 2 (2.06%) 0.881 Chronic renal insufficiency 9 (3.98%) 8 (8.25%) 0.116 Chronic renal failure 8 (3.54%) 7 (7.22%) 0.250 Cancer 14 (6.19%) 9 (9.28%) 0.323 Lumbar disease 15 (6.64%) 2 (2.06%) 0.091 Neck disease 6 (2.65%) 3 (3.09%) 1.000 Complications Acid base disturbance 124 (54.87%) 56 (57.73%) 0.635 Electrolyte imbalance 145 (64.16%) 68 (70.10%) 0.301 Anemia 135 (59.73%) 66 (68.04%) 0.158 Hypoproteinemia 189 (83.63%) 89 (91.75%) 0.053 Pleural effusion 196 (86.73%) 64 (65.98%) < 0.001* Acute myocardial infarction 7 (3.10%) 3 (3.09%) 1.000 Acute heart failure 19 (8.41%) 7 (7.22%) 0.718 Acute kidney injury 19 (8.41%) 8 (8.25%) 0.962 Acute liver injury 20 (8.85%) 12 (12.37%) 0.962 Hypovolemic shock 4 (1.77%) 2 (2.06%) 1.000 Septic shock 29 (12.83%) 16 (16.49%) 0.384 Cardiac shock 6 (2.65%) 0 (0.00%) 0.242 Laboratory results WBC (×10 9 /L) 8.8 (6.68–12.58) 9.7 (6.89–14.09) 0.299 RBC (×10¹²/L) 3.82 ± 0.83 3.62 ± 0.88 0.058 Hemoglobin (g/L) 117 (99.75-132.25) 112 (91.5-126.5) 0.163 Hematokrit (%) 36 (30.7–40.4) 33.3 (28.15–38.25) 0.011* Platelet count (×10 9 /L) 191 (133–246) 206 (131–275) 0.161 NEUT% 86.15 (78.23–90.6) 85.9 (77.7–90.5) 0.963 LY% 9.1 (5.08–14.64) 8.4 (5.05–15.2) 0.961 CRP (mg/L) 81.21 (33.03–161) 83.2 (30.88–157.9) 0.953 PCT (µg/L) 0.36 (0.12–1.3) 0.4 (0.2–1.92) 0.022* Total bilirubin (µmol/L) 13.2 (9.38–19.6) 12.3 (7.7–18.5) 0.156 Total protein (g/L) 59.38 ± 9.71 57.84 ± 7.49 0.123 Albumin (g/L) 31.5 ± 5.45 30.38 ± 4.95 0.082 ALT (U/L) 22.1 (13.45–37.4) 17 (11.15–27.25) 0.017* AST (U/L) 26.9 (17.38–44.55) 24 (17.7-46.45) 0.313 BUN (mmol/L) 7.39 (5.09–12.91) 9.22 (5.06–15.56) 0.209 Scr (µmol/L) 70.55 (52.05-106.33) 60 (46.05-109.55) 0.177 Potassium (mmol/L) 4.17 ± 0.75 4.07 ± 0.68 0.275 Sodium (mmol/L) 137.6 (134–141) 137 (134-141.4) 0.866 Troponin (ng/ml) 0.05 (0.02–0.1) 0.05 (0.03–0.09) 0.758 Myohemoglobin (ng/ml) 40.74 (28.38–69.83) 45.7 (44.7–73.6) 0.000* PT (s) 13.2 (11.9–14.8) 13.60 (11.95–15.40) 0.312 APTT (s) 33.20 (28.70–39.70) 31.90 (28.61–39.25) 0.393 Fibrinogen (g/L) 5.16 (3.79–6.49) 5.19 (3.81–6.55) 0.735 D-dimer (µg/ml) 2.29 (1.18–4.18) 1.87 (1.04–2.77) 0.009* BNP (pg/ml) 223 (81.57–814.5) 223 (119-635.5) 0.332 Arterial blood PH 7.44 (7.4–7.48) 7.45 (7.38–7.48) 0.364 PaO 2 (mmHg) 61.4 (55-75.65) 62.7 (58.9–80) 0.033* PaCO 2 (mmHg) 32.95 (28.93–39.08) 33 (31.1–36.9) 0.374 PaO 2 /FiO 2 229.5 (190.25–270) 230 (145.5–282) 0.931 Application of conventional medicine Glucocorticoids 127 (56.19%) 58 (59.79%) 0.549 Number of antibiotics ≥ 3 171 (75.66%) 58 (59.79%) 0.004* Beta-lactam antibiotics 222 (98.23%) 92 (94.85%) 0.185 Quinolone antibiotics 163 (72.12%) 44 (45.36%) < 0.001* Aminoglycoside antibiotics 26 (11.50%) 8 (8.25%) 0.382 Macrolide antibiotics 37 (16.37%) 15 (15.46%) 0.839 Tetracycline antibiotics 40 (17.70%) 22 (22.68%) 0.297 Sulfonamide antibiotics 1 (0.44%) 0 (0.00%) 1.000 Antifungal drug 72 (31.86%) 37 (38.14%) 0.273 Immunosuppressant 9 (3.98%) 2 (2.06%) 0.591 Conventional operation Fiber bronchoscope 107 (47.35%) 45 (46.39%) 0.875 Transfusion 52 (23.01%) 28 (28.87%) 0.264 Hemodialysis 12 (5.31%) 9 (9.28%) 0.185 ECMO 2 (0.88%) 1 (1.03%) 1.000 Tracheotomy 33 (14.60%) 17 (17.53%) 0.505 Retention catheterization 129 (57.08%) 60 (61.86%) 0.425 Gastric intubation 123 (54.42%) 57 (58.76%) 0.472 Deep vein catheterization 114 (50.44%) 49 (50.52%) 0.990 Days of nasal tube oxygen 2 (0–12) 0 (0–8) 0.077 Days of mask oxygen days 0 (0–0) 0 (0–0) 0.009* Days of non-invasive mechanical ventilation 0 (0–3) 0 (0–2) 0.505 Days of invasive mechanical ventilation 0 (0–7) 0 (0–6) 0.796 Days of mechanical ventilation 3 (0–11) 3 (0–10) 0.871 TCM or TCM appropriate technology Oral Chinese herbal decoction 166 (73.45%) 61 (62.89%) 0.064 Chinese patent medicine injection 181 (80.09%) 84 (86.60%) 0.162 TCM appropriate technology 190 (84.07%) 78 (80.41%) 0.423 TCM syndrome Phlegm-heat obstructing lung syndrome 78 (34.51%) 41 (42.27%) 0.354 Phlegm turbidity obstructing lung syndrome 43 (19.03%) 22 (22.68%) Deficiency of both qi and yin syndrome 23 (10.18%) 6 (6.19%) Lung-spleen qi deficiency syndrome 16 (7.08%) 11 (11.34%) Lung-spleen qi deficiency combined with phlegm turbidity obstructing lung syndrome 13 (5.75%) 3 (3.09%) Phlegm turbidity obstructing lung combined with stagnation of blood syndrome 9 (3.98%) 0 (0.00%) Deficiency of both qi and yin combined with phlegm turbidity obstructing lung syndrome 8 (3.54%) 3 (3.09%) Pathogenic qi falling into and prostration syndrome 7 (3.10%) 3 (3.09%) Invasion of pericardium by heat syndrome 6 (2.65%) 2 (2.06%) Phlegm-heat obstructing lung combined with stagnation of blood syndrome 6 (2.65%) 0 (0.00%) Deficiency of both qi and yin combined with phlegm-heat obstructing lung syndrome 6 (2.65%) 3 (3.09%) Lung-spleen qi deficiency combined with phlegm-heat obstructing lung syndrome 5 (2.21%) 1 (1.03%) Lung-spleen qi deficiency combined with stagnation of blood syndrome 4 (1.77%) 0 (0.00%) Stagnation of blood syndrome 1 (0.44%) 1 (1.03%) Deficiency of both qi and yin combined with stagnation of blood syndrome 1 (0.44%) 1 (1.03%) Others Multi-drug resistant bacterial infection 69 (30.53%) 31 (32.96%) 0.896 Total hospitalization days 16 (11–27) 15 (9.5–24.5) 0.266 Days of ICU stay 0 (0–7) 0 (0–7) 0.710 Features selection The LASSO regression identified 7 predictors from above 38 possible risk factors for 226 patients in the training set, according to the lambda.1se criterion for predictor selection, which was used for model construction (Fig. 1 ). All of the 7 predictors including age, TCM syndrome (pathogenic qi falling into and prostration syndrome), complication of septic shock, BNU level, tracheotomy application, retention catheterization application, and oral Chinese herbal decoction entered the final LR, SVM, DT, RF and XGBoost models. Model development, evaluation and comparison Discrimination The RF model demonstrated superior performance in the training set, attaining an accuracy of 0.982, a recall of 1.000, a precision of 0.941, an F1 score of 0.970, and an AUC of 0.999. The excessive high value of the indicators might be related to the overfitting of this model. The SVM indicators exhibited the lowest values among the five models, with an accuracy of 0.159, recall of 0.156, precision of 0.068, F1 score of 0.095, and AUC of 0.900. Moreover, the AUC of all five prediction models over 0.9, signifying a strong fitting performance in the training set. In the test set, the SVM model showed significantly inferior accuracy, recall, precision, and F1 score compared to other models, yet had the best AUC. The RF model revealed superior performance in accuracy, recall, precision, and F1 score metrics, with an AUC value ranking second only to the SVM model among the five models. Furthermore, the XGBoost model had the third best AUROC (0.853). The predicted value of the XGBoost model exceeded that of the Pneumonia Severity Index (PSI), SOFA, and APACHE II scoring systems, which showed AUC values of 0.808, 0.819, and 0.837, respectively. The comprehensive results of the discrimination among the five models presented in Table 4 , while the ROC curves are illustrated in Figs. 2 and 3 . The DeLong test showed that there were significant differences in AUC between the RF model and others in the training set, also between the XGBoost and SVM models ( P 0.05). The results of DeLong test illustrated in Fig. 4 . Table 4 Comparing the discrimination of the five severe pneumonia hospital mortality prediction models Model Training Set ( n = 226) Test Set ( n = 97) Accuracy Recall Precision F1 score AUC Accuracy Recall Precision F1 score AUC LR 0.845 0.844 0.684 0.755 0.904 0.732 0.793 0.535 0.639 0.844 SVM 0.159 0.156 0.068 0.095 0.900 0.247 0.103 0.060 0.076 0.877 DT 0.854 0.844 0.594 0.697 0.904 0.753 0.609 0.483 0.539 0.802 RF 0.982 1.000 0.941 0.970 0.999 0.773 0.793 0.590 0.677 0.855 XGBoost 0.788 0.906 0.580 0.707 0.929 0.701 0.897 0.500 0.642 0.853 Calibration In the training set, the DT model exhibited the most optimal calibration, succeeded by XGBoost, LR, RF, and SVM models. In the test set, the calibration performance ranked from highest to lowest as follows: XGBoost, RF, LR, DT, and SVM model (Fig. 5 ). Clinical practicability In the training set, the net benefit of the RF model exceeded that of the DT, LR, XGBoost, and SVM models as indicated by the DCA. In the test set, the XGBoost model exhibited the highest net benefit, while the SVM model performed the poorest, indicating that the XGBoost model was the most optimal. Moreover, with the exception of the SVM model, DCA curves showed that the other four models demonstrate clinical value (Fig. 6 ). Optimal model analysis In comparison to the other four models, the XGBoost model demonstrated the third highest AUROC (0.853), along with optimal calibration and clinical applicability. The DCA curve indicated potential clinical benefit in predicting hospital mortality in patients with severe pneumonia. Thus, the XGBoost model emerged as the optimal selection, evaluated comprehensively across the dimensions of discrimination, calibration, and clinical practicability. SHAP values were calculated for the XGBoost prediction model to assess the significance of variables and the validity of internal algorithm. The application of retention catheterization exhibited the highest predictive value across all forecasting horizons, succeeded by the variables of oral Chinese herbal decoction, BUN level, age, application of tracheotomy, complication of septic shock, and TCM syndrome (pathogenic qi falling into and prostration syndrome). Furthermore, raised BUN levels and age, along with complication of septic shock, the application of retention catheterization, and TCM syndrome (pathogenic qi deficiency and prostration syndrome), positively influenced mortality predictions. Conversely, the application of tracheotomy and oral Chinese herbal decoction negatively affected mortality predictions, indicating a tendency toward survival. The SHAP values of the seven predictors in the XGBoost model illustrated in Fig. 7 . Discussion Principal findings Our study retrospectively gathered clinical data from 226 patients with severe pneumonia for the training set, of whom 64 died in-hospital, resulting in a mortality of 28.32%, consistent with findings from prior studies 26 . The Lasso regression analysis was conducted to identify risk factors associated with severe pneumonia mortality in relation to Chinese and conventional medicine, including age, complication of septic shock, BNU level, TCM syndrome (pathogenic qi falling into and prostration syndrome), application of tracheotomy, retention catheterization, and oral Chinese herbal decoction. The implementation of tracheotomy and the administration of oral Chinese herbal decoction are protective variables influencing the mortality outcomes of patients with severe pneumonia. We constructed and validated models capable of predicting mortality in patients with severe pneumonia using routinely available clinical data, and compared five machine learning algorithms. The XGBoost model is superior to the overall performance of LR, SVM, DT, RF, as well as the scoring systems of PSI, SOFA, and APACHE II. The SHAP method explains the XGBoost model, so enhancing both model performance and clinical interpretability. This model may possess potential utility in personalized surveillance prognosis, facilitating improved therapy schedules and appropriate resource allocation for patients. Machine learning is characterized by its applicability to various types of datasets, resulting in its widespread utilization. Nonetheless, various algorithms possess distinct benefits, and their capacity and efficacy in problem-solving mostly depend on the characteristics of data aspects and the performance of algorithms. Consequently, evaluating the efficacy of various machine learning algorithms on a particular dataset to identify the ideal model, together with employing feature importance analysis to enhance comprehension of presented features, is highly significant 27 . The most significant predictive factor in the optimal XGBoost model is the application of retention catheterization, succeeded by oral Chinese herbal decoction, BUN level, age, tracheotomy application, complication of septic shock, and TCM syndrome (pathogenic qi falling into and prostration syndrome). Patients with severe pneumonia frequently present with multiple underlying diseases, and those in critical condition often suffer from consciousness disorders, hindering their ability to urinate autonomously; thus, the application of retention catheterization is required. However, this study identified that indwelling catheters are an important risk factor for mortality due to severe pneumonia, corroborating findings from previous studies 28 . Recent studies have demonstrated that TCM, when combined with conventional treatment, offers improvements in the management of severe pneumonia 29 . Our research showed that a duration of over 5 days of oral Chinese herbal decoction might decrease the mortality risk of severe pneumonia, hence revealing the efficacy of TCM for treating severe pneumonia based on syndrome differentiation. BUN is a primary end product of protein metabolism in the human body and serves as a crucial indication for assessing kidney function. The lung and kidney exhibit complex connections, both playing crucial organs in regulating acid-base and fluid balance 30 . In addition, any impairment to the kidneys can substantially impact the lungs by disturbing normal the pH and fluid distribution balance. Furthermore, the kidneys may promote the progression and regulate of pulmonary illnesses by the production or elimination of mediators. The interaction between the lungs and kidneys highlights their mutual dependence and impact on overall physiological function 31 . A study indicated that patients with acute kidney injury and pneumonia exhibited a greater mortality compared to those with either condition alone 32 . Furthermore, a diagnostic criterion for severe pneumonia includes BUN levels, signifying a strong association between BUN and disease severity. Our study demonstrates that BUN is a significant risk factor for increased mortality in patients with severe pneumonia, potentially attributable to the relationship between the lung microbiome in these patients and kidney damage 33 . With advancing age, the human immune system experiences various alterations, resulting in diminished capacity to efficiently trigger cellular responses against pathogens. The chemotactic capacity of polymorphonuclear leukocytes in the elderly is weakened, and the microbial uptake and antigen processing capabilities of macrophages are correspondingly reduced 34 . Moreover, age-related factors such as chronic comorbidities, alterations in immunological physiology, and malnutrition substantially increase the risk of infection in the elderly 35 . The results of this study indicate that the risk of mortality from severe pneumonia increases with age, which is consistent with previous research findings 36 and potentially linked to age-associated chronic disorders and/or diminished immune function 37 . Individuals with severe pneumonia display a substantial elevation in airway secretions. When accompanied with consciousness problems, severe cerebral infarction, traumatic brain injury, or additional problems, respiratory function becomes impaired, requiring ventilator support. Elderly patients, due to their numerous medical conditions, are susceptible to difficulties such as the accumulation of airway secretions, respiratory obstruction, and throat injury during prolonged laryngotracheal intubation, potentially resulting in complications such ventilator-associated pneumonia 38 . Therefore, for severe pneumonia patients on prolonged ventilator support with stable conditions, tracheotomy may be considered if extended ventilatory assistance is essential. Our study found that tracheotomy serves as a preventive factor against mortality associated with severe pneumonia, significantly reducing the risk of death. Nonetheless, owing to limitations in clinical data collection, the precise best present moment for incision requires additional investigation. Pneumonia is the major cause of septic shock, responsible for 50% of cases 39 – 42 . A retrospective clinical survey of 710 patients indicated that the mortality for individuals with severe pneumonia complicated with septic shock was greater than for those without septic shock 41 . Our study identified concurrent septic shock as a significant risk factor for increased mortality in patients with severe pneumonia, corroborating findings from prior research 42 and mutually confirming that septic shock is one of the two primary diagnostic criteria for severe pneumonia 43 . TCM syndromes serve as significant indicators for disease progression, aiding in the prognostic assessment of patients according to their syndrome classifications or developments 44 . Previous studies have shown that common symptoms of severe pneumonia include phlegm-heat obstructing lung syndrome, deficiency of both qi and yin syndrome, pathogenic qi falling into and prostration syndrome, and phlegm turbidity obstructing lung syndrome 45 . Our study identified that the pathogenic qi falling into and prostration syndrome were risk factors for mortality in severe pneumonia, with the presence of this syndrome frequently indicating a fatal outcome. Strengths compared to previous constructed models Currently, multiple predictive models exist concerning the mortality risk associated with severe pneumonia. We did a thorough search and systematic comparison, revealing that the model we developed possesses particular characteristics and advantages. A study established the LR, gradient-boosted decision tree (LightGBM), and multilayer perceptron (MLP) models to forecast ICU mortality in patients with severe pneumonia 48 . The best MLP model achieved an AUC of 0.838, which was inferior than the AUC of 0.853 obtained by our XGBoost model. Both studies constructed multivariable LR models with an AUC of 0.836 46 and 0.728 47 for predicting in-hospital mortality in elderly patients with severe community-acquired pneumonia (SCAP). Additionally, another LR model, which lacked validation, reported an AUC as high as 0.915 in the training set 47 . A study 48 exclusively employed the LR method rather than machine learning algorithms to develop an in-hospital mortality risk prediction model for patients with SCAP. An alternative LR model predicting 30-day mortality in ICU patients with SCAP exhibited a lower AUC of 0.756 49 . Nevertheless, our research additionally produced four models: SVM, DT, RF, and XGBoost, with the performance of our best model superior than that of models developed in prior studies. In summary, the model we developed possesses the following advantages: First of all, we employed multiple algorithms for machine learning, including SVM, DT, RF, and XGBoost, rather than solely relying on LR, and identified the optimal XGBoost model. Secondly, the optimal model we have developed exhibits markedly superior discrimination compared to previously published models, with an AUC of 0.853. Thirdly, and most importantly, prior models failed to incorporate TCM features, whereas our study first gathered 115 clinical features. Among the seven risk factors linked to in-hospital mortality in severe pneumonia identified by LASSO regression, two were TCM factors: TCM syndrome (pathogenic qi dropping into and prostration syndrome) and oral Chinese herbal decoction. Consequently, our model could provide a more comprehensive review of the severe pneumonia patients state and yield reliable predictions. Limitations Our study also has certain limitations. Initially, the absence of partial clinical data can lead to certain biases in the final outcomes. Our study depended on a retrospective research database. To ensure the reliability and accuracy of the research conclusions, our team cautiously managed quality control during data collection to acquire patient clinical data comprehensively and objectively. Despite employing different approaches to modeling and prospective validation, it remains impossible to eliminate issues such as missing clinical data records from the source, potentially resulting in biases in the final outcomes. Secondly, the sample size is rather limited. Clinical data for our investigation were acquired from two large hospitals. Despite the screening period starting in January 2008, the final sample size remained relatively small comparing to other diseases due to restricted medical conditions. A larger sample size in predictive model development provides more accurate findings. Consequently, we look forward to undertaking large-scale studies in multiple regions and institutions nationwide. Thirdly, not all machine learning algorithms are applied in this study. Our study selected five frequently employed algorithms and performed comparisons, but there are many machine learning algorithms that exist, and other algorithms such as Naive Bayes, Artificial Neural Networks, K-NN, etc. not used. Thus, we expect to investigate other machine learning techniques in the future to thoroughly assess and develop a more effective integrated risk model for severe pneumonia mortality, combining traditional Chinese and conventional treatment. Conclusions Older age, increased BNU level, complication of septic shock, tracheotomy application, retention catheterization application, oral Chinese herbal decoction, and TCM syndrome (pathogenic qi falling into and prostration syndrome) may be potential risk factors that affect mortality in severe pneumonia, among which tracheotomy application and oral Chinese herbal decoction are protective factors. The XGBoost model exhibits superior overall performance in predicting hospital mortality risk for severe pneumonia, greater than traditional scoring systems such as PSI, SOFA, and APACHE II, which assists clinicians in prognostic assessment, resulting in improved therapeutic strategies and optimal resource allocation for patients. Abbreviations ICU, intensive care unit; CRP, C-reactive protein; IL, interleukin; mNUTRIC, Modified Nutrition Risk in Critically ill; TCM, traditional Chinese medicine; AI, artificial intelligence; SOFA, Sequential Organ Failure Assessment; APACHE II, Acute Physiology and Chronic Health Evaluation II; LR, Logistic Regression; SVM, Support Vector Machine; DT, Decision Tree; RF, Random Forest; XGBoost, Extreme Gradient Boosting; H1N1, Influenza A; SARS, severe acute respiratory syndrome; COVID-19, coronavirus disease 2019; COPD, chronic obstructive pulmonary disease; WBC, white blood cell; RBC, red blood cell; NEUT%, neutrophilic granulocyte percentage; LY%, lymphocyte percentage; PCT, procalcitonin; AST, aminotransferase; ALT, alanine aminotransferase; BUN, blood urea nitrogen; Scr, serum creatinine; PT, prothrombin time; BNP, brain natriuretic peptide; PaO 2 ,arterial partial pressure of oxygen; PaCO 2 , arterial partial pressure of carbon dioxide; PaO 2 /FiO 2 , arterial oxygenation index; SD, standard deviation; IQR, interquartile range; LASSO, Least Absolute Shrinkage and Selection Operator; AUROC, area under the receiver operating characteristic; ROC, receiver operation characteristic; AUC, area under the curve; DCA, decision curve analysis; PSI, Pneumonia Severity Index; SHAP, SHapley Additive exPlanations; LightGBM, gradient-boosted decision tree; MLP, multilayer perceptron; SCAP, severe community acquired pneumonia. Declarations Data Availability Statement Due to confidentiality, data collected for the study are not publicly available for download. For further inquiries, please contact the corresponding author. Acknowledgements This study was supported by the National Natural Science Foundation of China (No. 81774222, 82074411), Special Research Project of Traditional Chinese Medicine in Henan Province (No. 2023ZY1005), Construction project of traditional Chinese medicine in Henan Province (No. STG-ZYX02-202204), Henan University of Traditional Chinese Medicine’s Top Level Creation of Engineering Respiratory Disease Prevention and Treatment Technology Innovation Team in Traditional Chinese Medicine (No. HSRP-DFCTCM-T-1), Henan Province Traditional Chinese Medicine Top Level to Creation of a special scientific research topic (No. HSRP-DFCTCM-2023-3-21, HSRP-DFCTCM-2023-8-06). Author contributions Kai Xie wrote the original draft, analysed and interpreted the data. Xiajin Huang, Zhen Li, Wenjing Yin, Xiaoxuan He, Xinyu Miao were responsible for the participants recruitment, information record, and data extraction. Haifeng Wang contributed to the study design and revised the manuscript. All authors read and approved the publication of this study. Competing interests The authors declare that there is no conflict of interest regarding the publication of this paper. Ethical approval This study was approved by the Ethics Committee of the First Affiliated Hospital of Henan University of Chinese Medicine (No. 2023HL-241-01). Consent for Publication All participants provided consent for the publication of findings. Additional information Correspondence and requests for materials should be addressed to Haifeng Wang. References Abbas, K., Aboyans, M., Ackerman, I. & V., & Global burden of 369 diseases and injuries in 204 countries and territories, 1990–2019: a systematic analysis for the global burden of disease study 2019. Lancet 396 , 1204–1222 (2020). Welte, T., Torres, A. & Nathwani, D. Clinical and economic burden of community-acquired pneumonia among adults in Europe. Thorax 67 , 71–79 (2012). Aliberti, S. et al. Global initiative for meticillin-resistant staphylococcus aureus pneumonia (GLIMP): an international, observational cohort study. Lancet. Infect. Dis . 16 , 1364–1376 (2016). Martin-Loeches, I., Garduno, A., Povoa, P. & Nseir, S. Choosing antibiotic therapy for severe community-acquired pneumonia. Curr. Opin. Infect. Dis. 35 , 133–139 (2022). Chen, J. et al. High mean platelet volume associates with in-hospital mortality in severe pneumonia patients. Mediat. Inflamm. (2020). (2020). Huang, D. et al. Association of admission lactate with mortality in adult patients with severe community-acquired pneumonia. Am. J. Emerg. Med. 65 , 87–94 (2023). Zhang, C., Zheng, F. & Wu, X. Predictive value of C-Reactive protein-to-albumin ratio for risk of 28-day mortality in patients with severe pneumonia. J. Lab. Med. 47 , 115–120 (2023). Espana, P. P. et al. Development and validation of a clinical prediction rule for severe community-acquired pneumonia. Am. J. Respir Crit. Care Med. 174 , 1249–1256 (2006). Acehan, S. et al. MNUTRIC tool is capable to predict nutritional needs and mortality early in patients suffering from severe pneumonia. Clin. Nutr. ESPEN . 45 , 184–191 (2021). Miao, L., Shen, X., Du, Z. & Liao, J. Stress hyperglycemia ratio and its influence on mortality in elderly patients with severe community-acquired pneumonia: a retrospective study. Aging Clin. Exp. Res. 36 , 175 (2024). Lu, R. et al. Serum krebs von den lungen-6 is associated with in-hospital mortality of patients with severe community-acquired pneumonia: a retrospective cohort study. Clin. Chim. Acta . 548 , 117524 (2023). Tseng, C. C. et al. The importance of high total body water/fat free mass ratio and serial changes in body composition for predicting hospital mortality in patients with severe pneumonia: a prospective cohort study. BMC Pulm Med. 24 , 470 (2024). Dos Santos Medeiros, S. M. D. F. et al. Predictive biomarkers of mortality in patients with severe COVID-19 hospitalized in intensive care unit. Front. Immunol. 15 , 1416715 (2024). Lee, J. et al. Severe thinness is associated with mortality in patients with community-acquired pneumonia: a prospective observational study. Am. J. Emerg. Med. 33 , 209–213 (2015). Que, Y. A. et al. Low C-reactive protein values at admission predict mortality in patients with severe community-acquired pneumonia caused by streptococcus pneumoniae that require intensive care management. Infection 43 , 193–199 (2015). Xie, K. et al. Predictors of mortality in severe pneumonia patients: a systematic review and meta-analysis. Syst. Rev. 13 , 210 (2024). Ranstam, J., Cook, J. A. & Collins, G. S. Clinical prediction models. Br. J. Surg. 103 , 1886 (2016). Li, J. et al. Machine learning prediction model for acute renal failure after acute aortic syndrome surgery. Front. Med. 8 , 728521 (2021). Bi, Q., Goodman, K. E., Kaminsky, J. & Lessler, J. What is machine learning? a primer for the epidemiologist. Am. J. Epidemiol. 188 , 2222–2239 (2019). Pirracchio, R. et al. Mortality prediction in intensive care units with the super icu learner algorithm (sicula): a population-based study. Lancet Resp. Med. 3 , 42–52 (2015). Chinese Medical Association of respiratory disease branch. Diagnosis and treatment guidelines for adult community acquired pneumonia in China (2016 Edition). C J. T R D . 39 , 253–279 (2016). Metlay, J. P. et al. Diagnosis and treatment of adults with community-acquired pneumonia. an official clinical practice guideline of the American thoracic society and infectious diseases society of America. Am. J. Respir Crit. Care Med. 200 , e45–e67 (2019). Yu, X., Xie, Y. & Li, J. Guidelines for the diagnosis and treatment of community-acquired pneumonia (2018 Revision). J. T C M . 60 , 350–360 (2019). LASSO, R. R. R., M. A feature selection technique in predictive modeling for machine learning. IEEE International Conference on Advances in Computer Applications (ICACA) , 2016:18–20. (2016). Van Calster, B. et al. Reporting and interpreting decision curve analysis: a guide for investigators. Eur. Urol. 74 , 796–804 (2018). Kassaw, G. et al. Outcomes and predictors of severe community-acquired pneumonia among adults admitted to the university of gondar comprehensive specialized hospital: a prospective follow-up study. Infect. Drug Resist. 16 , 619–635 (2023). Domaratzki, M. & Kidane, B. Deus Ex Machina? demystifying rather than deifying machine learning. J. Thorac. Cardiovasc. Surg. 163 , 1131–1137 (2022). Zhu, W. et al. Delirium in hospitalized COVID-19 patients: a prospective, multicenter, cohort study. J. Neurol. 270 , 4608–4616 (2023). Xie, K. et al. efficacy and safety of traditional chinese medicine adjuvant therapy for severe pneumonia: evidence mapping of the randomized controlled trials, systematic reviews, and meta-analyses. Front. Pharmacol. 14 , 1227436 (2023). Hepokoski, M. L., Bellinghausen, A. L., Bojanowski, C. M. & Malhotra, A. Can we DAMPen the cross-talk between the lung and kidney in the icU? Am. J. Respir Crit. Care Med. 198 , 1220–1222 (2018). Wang, Z., Pu, Q., Huang, C. & Wu, M. Crosstalk between lung and extrapulmonary organs in infection and inflammation. Adv. Exp. Med. Biol. 1303 , 333–350 (2021). Chawla, L. S. et al. Impact of acute kidney injury in patients hospitalized with pneumonia. Crit. Care Med. 45 , 600–606 (2017). Du, S. et al. Clinical factors associated with composition of lung microbiota and important taxa predicting clinical prognosis in patients with severe community-acquired pneumonia. Front. Med. 16 , 389–402 (2022). Mahendra, M. et al. Factors influencing severity of community-acquired pneumonia. Lung India . 35 , 284–289 (2018). Arvaniti, K. et al. Epidemiology and age-related mortality in critically Ill patients with intra-abdominal infection or sepsis: an international cohort study. Int. J. Antimicrob. Agents . 60 , 106591 (2022). Li, Y., Wang, C. & Peng, M. Aging immune system and its correlation with liability to severe lung complications. Front. Public. Health . 9 , 735151 (2021). Wang, K. et al. Clinical and laboratory predictors of in-hospital mortality in patients with coronavirus disease-2019: a cohort study in wuhan, China. Clin. Infect. Dis. 71 , 2079–2088 (2020). Kaese, S., Zander, M. C. & Lebiedz, P. Successful use of early percutaneous dilatational tracheotomy and the no sedation concept in respiratory failure in critically ill obese subjects. Respir Care . 61 , 615–620 (2016). Guzzardella, A., Motos, A., Vallverdu, J. & Torres, A. Corticosteroids in sepsis and community-acquired pneumonia. Med. Klin. Intensivmed Notfmed . 118 , 86–92 (2023). Spencer, E., Rosengrave, P., Williman, J., Shaw, G. & Carr, A. C. Circulating protein carbonyls are specifically elevated in critically ill patients with pneumonia relative to other sources of sepsis. Free Radic Biol. Med. 179 , 208–212 (2022). Güell, E. et al. Impact of lymphocyte and neutrophil counts on mortality risk in severe community-acquired pneumonia with or without septic shock. J. Clin. Med. 8 , (2019). Espinoza, R. et al. Factors associated with mortality in severe community-acquired pneumonia: a multicenter cohort study. J. Crit. Care . 50 , 82–86 (2019). Ferrer, M. et al. Severe community-acquired pneumonia: characteristics and prognostic factors in ventilated and non-ventilated patients. PLoS One 13 , (2018). Lu, Y. & Deng, M. Inspiration from golden chamber synopsis for critically ill disease prognosis. J. T C M . 58 , 661–663 (2017). Zhang, C., Guan, S., Xie, K., Zhang, K. & Wang, H. Distribution of clinical traditional Chinese medicine syndromes in patients with severe community-acquired pneumonia. Chin. Gen. Pract. 25 , 2640–2645 (2022). Shang, N., Li, Q., Liu, H., Li, J. & Guo, S. Erector spinae muscle-based nomogram for predicting in-hospital mortality among older patients with severe community-acquired pneumonia. BMC Pulm Med. 23 , 346 (2023). Zhu, Y. et al. Mortality Prediction using clinical and laboratory features in elderly patients with severe community-acquired pneumonia. Ann. Palliat. Med. 10 , 10913–10921 (2021). Pan, J., Bu, W., Guo, T., Geng, Z. & Shao, M. Development and validation of an in-hospital mortality risk prediction model for patients with severe community-acquired pneumonia in the intensive care unit. BMC Pulm Med. 23 , 303 (2023). Zhang, Y., Peng, Y., Zhang, W. & Deng, W. Development and validation of a predictive model for 30-day mortality in patients with severe community-acquired pneumonia in intensive care units. Front. Med. 10 , 1295423 (2023). 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-5685118","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":439081266,"identity":"0e77d1f2-4007-4c9d-8ae9-a0d6a4d66498","order_by":0,"name":"Kai Xie","email":"","orcid":"","institution":"The First Affiliated Hospital of Henan University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Kai","middleName":"","lastName":"Xie","suffix":""},{"id":439081267,"identity":"e6c371f3-f495-4210-8bff-a504afb62ba8","order_by":1,"name":"Xiajin Huang","email":"","orcid":"","institution":"The First Affiliated Hospital of Henan University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Xiajin","middleName":"","lastName":"Huang","suffix":""},{"id":439081268,"identity":"8c9893ab-a19b-4b4f-b65c-68d483468562","order_by":2,"name":"Zhen Li","email":"","orcid":"","institution":"The First Affiliated Hospital of Henan University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Zhen","middleName":"","lastName":"Li","suffix":""},{"id":439081269,"identity":"279d26cd-2402-46fe-8e8e-c91bf1a9ebd9","order_by":3,"name":"Wenjing Yin","email":"","orcid":"","institution":"The First Affiliated Hospital of Henan University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Wenjing","middleName":"","lastName":"Yin","suffix":""},{"id":439081270,"identity":"5002aa91-82dd-49c3-a5ad-7ec83d699db7","order_by":4,"name":"Xiaoxuan He","email":"","orcid":"","institution":"The First Affiliated Hospital of Henan University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Xiaoxuan","middleName":"","lastName":"He","suffix":""},{"id":439081271,"identity":"cb2793e3-3af3-4f1e-bb56-e389bb9dcd69","order_by":5,"name":"Xinyu Miao","email":"","orcid":"","institution":"The First Affiliated Hospital of Henan University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Xinyu","middleName":"","lastName":"Miao","suffix":""},{"id":439081272,"identity":"8642d5e6-39cc-41a6-b03c-128b238da08b","order_by":6,"name":"Haifeng Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAuElEQVRIiWNgGAWjYJACZgYGOTk29uYDJGkxNubjOZZAmpbEeRI5CsQpNzh+9vDrAgaD9DaGHAaGHxXbiNByJi/NegaDQW4bw9kDjD1nbhPWYnYgx8yYh+FPbhtjXwIzYxsxWs6/AWkxSGdj5jEgUsuNHOPHQC0JbGzEarG/8caMGajFsI2HLeEgUX6R7M8x/gzUIi8///HBBz8qiNACBGwSjP8grANEqQcC5g/EqhwFo2AUjIIRCgDfgDVLtlugnwAAAABJRU5ErkJggg==","orcid":"","institution":"The First Affiliated Hospital of Henan University of Chinese Medicine","correspondingAuthor":true,"prefix":"","firstName":"Haifeng","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2024-12-20 15:08:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5685118/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5685118/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":80063309,"identity":"4ca0b5e0-9a13-4a95-b3b9-b935fa5f809b","added_by":"auto","created_at":"2025-04-07 12:43:34","extension":"jpg","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":119944,"visible":true,"origin":"","legend":"\u003cp\u003eSelection of predictors by LASSO regression analysis with 10-fold cross-validation. (A) A coefficient profile plot was generated against the log (lambda) sequence. (B) The selection of the parameter (lambda) of deviance in LASSO regression was tuned according to the minimum and 1se criterion, indicated by the left and right dotted lines, respectively.\u003c/p\u003e","description":"","filename":"Fig.1.SelectionofpredictorsbyLASSOregressionanalysiswith10foldcrossvalidation.jpg","url":"https://assets-eu.researchsquare.com/files/rs-5685118/v1/aa1c6f4bd9f5a0a034d02fff.jpg"},{"id":80063320,"identity":"9378df12-5597-4b2b-9232-645d587f2026","added_by":"auto","created_at":"2025-04-07 12:43:35","extension":"jpg","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":1351843,"visible":true,"origin":"","legend":"\u003cp\u003eComparison of ROC curves between different models in the training set (A) and test set (B).\u003c/p\u003e","description":"","filename":"Fig.2.ComparisonofROCcurvesbetweendifferentmodelsinthetrainingsetAandtestsetB1.jpg","url":"https://assets-eu.researchsquare.com/files/rs-5685118/v1/322562e7f8e309c25c57710d.jpg"},{"id":80064115,"identity":"6113b01b-19e4-474f-a07c-845e70258ed4","added_by":"auto","created_at":"2025-04-07 12:51:34","extension":"jpg","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":52179,"visible":true,"origin":"","legend":"\u003cp\u003eComparison of ROC curves between different scoring systems of the PSI, SOFA, and APACHE Ⅱin the test set.\u003c/p\u003e","description":"","filename":"Fig.3.ComparisonofROCcurvesbetweendifferentscoringsystemsofthePSISOFAandAPACHEinthetestset..jpg","url":"https://assets-eu.researchsquare.com/files/rs-5685118/v1/5be8591fd41f0e9ee1a37be0.jpg"},{"id":80064117,"identity":"2d557d0c-e621-4249-8621-34223d01e0a4","added_by":"auto","created_at":"2025-04-07 12:51:35","extension":"jpg","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":169975,"visible":true,"origin":"","legend":"\u003cp\u003eComparison of AUC valuesby DeLong test between different models in the training set (A) and test set (B).\u003c/p\u003e","description":"","filename":"Fig.4.ComparisonofAUCvaluesbyDeLongtestbetweendifferentmodelsinthetrainingsetAandtestsetB..jpg","url":"https://assets-eu.researchsquare.com/files/rs-5685118/v1/28d310b4b88acf9ad1314842.jpg"},{"id":80063314,"identity":"03b27604-f77c-486f-a16f-dc62825c8816","added_by":"auto","created_at":"2025-04-07 12:43:35","extension":"jpg","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":128232,"visible":true,"origin":"","legend":"\u003cp\u003eComparison of calibration curves between different models in the training set (A) and test set (B).\u003c/p\u003e","description":"","filename":"Fig.5.ComparisonofcalibrationcurvesbetweendifferentmodelsinthetrainingsetAandtestsetB..jpg","url":"https://assets-eu.researchsquare.com/files/rs-5685118/v1/75d1b13cf284bb03971b5e07.jpg"},{"id":80065210,"identity":"e96fae46-4c78-44af-a8ef-ed62ca5ae094","added_by":"auto","created_at":"2025-04-07 13:07:35","extension":"jpg","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":95658,"visible":true,"origin":"","legend":"\u003cp\u003eComparison of DCA between different models in the training set (A) and test set (B). X-axis indicates the threshold probability and Y-axis indicates the net benefit. The dashed gray line indicates that all severe pneumonia patients had hospital death, while the dashed yellow line indicates that no patient had hospital death.\u003c/p\u003e","description":"","filename":"Fig.6.ComparisonofDCAbetweendifferentmodelsinthetrainingsetAandtestsetB..jpg","url":"https://assets-eu.researchsquare.com/files/rs-5685118/v1/bb0a4a2109c643a780693e38.jpg"},{"id":80064118,"identity":"b283e371-6c5a-4d31-a555-3e3b1c93eb3d","added_by":"auto","created_at":"2025-04-07 12:51:35","extension":"jpg","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":126791,"visible":true,"origin":"","legend":"\u003cp\u003eSHAP value of the seven variables in XGBoostModel. The bar graph on the left side showed the mean absolute value of SHAP in each variable. The names of variables displayed in the middle in order of mean absolute value of SHAP.\u003c/p\u003e","description":"","filename":"Fig.7.SHAPvalueofthesevenvariablesinXGBoostModel.jpg","url":"https://assets-eu.researchsquare.com/files/rs-5685118/v1/083109510cf7c94db671d454.jpg"},{"id":85916682,"identity":"0367f5a9-e346-4f93-bd2e-0eb7a8e096bb","added_by":"auto","created_at":"2025-07-03 07:01:58","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4157391,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5685118/v1/bd340993-9012-454f-b755-70d64d4f616c.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Development and validation of a clinical prediction model for in-hospital mortality of severe pneumonia based on machine learning","fulltext":[{"header":"Introduction","content":"\u003cp\u003eThe 2019 Global Burden of Disease Study indicated that lower respiratory infections ranked as the fourth major cause of global mortality, resulting in over 2.49 million deaths, beaten only by newborn illnesses, ischemic heart disease, and stroke \u003csup\u003e1\u003c/sup\u003e. Severe pneumonia is a frequently occurring life-threatening disease characterized by lower respiratory infection, with a high mortality, numerous complications, a poor prognosis, and a significant economic burden\u0026nbsp;\u003csup\u003e2\u003c/sup\u003e. Furthermore, it is a primary cause of ICU hospitalization and infection-related death around the world\u0026nbsp;\u003csup\u003e3\u003c/sup\u003e. In the United States, pneumonia causes 78% of infection-related deaths\u0026nbsp;\u003csup\u003e4\u003c/sup\u003e. Despite continuous breakthroughs in therapy over the last few decades, severe pneumonia has always been linked with a significant death rate, ranging from 20% to more than 50%\u0026nbsp;\u003csup\u003e5\u003c/sup\u003e. Thus, the identification of early hospital mortality risk in patients with severe pneumonia is essential and may facilitate appropriate care and clinical decision support.\u003c/p\u003e\n\u003cp\u003eIn recent years, identifying mortality risk factors in patients with severe pneumonia has emerged as the main study focus. Researchers have discovered several factors associated with mortality in patients with severe pneumonia, including high mean platelet volume levels\u0026nbsp;\u003csup\u003e5\u003c/sup\u003e, increased admission lactate\u0026nbsp;\u003csup\u003e6\u003c/sup\u003e, C-reactive protein (CRP)-to-albumin ratio\u0026nbsp;\u003csup\u003e7\u003c/sup\u003e, admission interleukin (IL)-32 concentration\u0026nbsp;\u003csup\u003e8\u003c/sup\u003e, the Modified Nutrition Risk in Critically ill (mNUTRIC) score\u0026nbsp;\u003csup\u003e9\u003c/sup\u003e, elevated stress hyperglycemia ratio\u0026nbsp;\u003csup\u003e10\u003c/sup\u003e, serum Krebs von den Lungen-6\u0026nbsp;\u003csup\u003e11\u003c/sup\u003e, the ratio of total body water to fat-free mass\u0026nbsp;\u003csup\u003e12\u003c/sup\u003e, thrombocytopenia\u0026nbsp;\u003csup\u003e13\u003c/sup\u003e, severe thinness (Body Mass Index \u0026lt;16 kg/m\u003csup\u003e2\u003c/sup\u003e)\u0026nbsp;\u003csup\u003e14\u003c/sup\u003e, and the presence of septic shock\u0026nbsp;\u003csup\u003e15\u003c/sup\u003e. Nevertheless, these factors are comparatively singular and varied. Despite a systematic review that comprehensively analyze existing literature to identify mortality risk factors for severe pneumonia\u0026nbsp;\u003csup\u003e16\u003c/sup\u003e, there is an absence of precise prediction applicable to individual cases.\u003c/p\u003e\n\u003cp\u003eThe clinical prediction model can estimate the probability of a specific individual currently suffering from a certain condition or experiencing a certain outcome in the future by assigning relative weights to each predictor variable and combining multiple predictor variables\u0026nbsp;\u003csup\u003e17\u003c/sup\u003e. There has been an increasing number of studies on prediction models worldwide. However, there is an absence of predictive models regarding the mortality risk associated with severe pneumonia that contain traditional Chinese medicine (TCM) characteristics, as well as inadequate comparisons among existing models; moreover, selection and consideration of predictive variables are insufficient. Hence, it is crucial to develop a comprehensive and systematic mortality risk prediction model for severe pneumonia containing TCM characteristics. Based on clinical needs, constructing prediction models can greatly promote the implementation of precision medicine, support thorough clinical diagnosis and evidence-based decision-making, and optimize public health resources allocation.\u003c/p\u003e\n\u003cp\u003eThe advancement of electronic medical record systems has helped in the availability of substantial clinical data. Nonetheless, conventional logistic regression is incapable of managing complex clinical data\u0026nbsp;\u003csup\u003e18\u003c/sup\u003e. Currently, artificial intelligence (AI) technology has achieved substantial breakthroughs, introducing novel techniques for data processing and extraction. Machine learning, a core component of AI, can autonomously develop data models, recognize complex data patterns, and predict results based on insights derived from computer algorithms\u0026nbsp;\u003csup\u003e19\u003c/sup\u003e. Due to the inherent capabilities of machine learning algorithms, an increasing number of researchers support the implementation of novel predictive models based on machine learning to facilitate suitable diagnosis and treatment, compared to conventional illness severity classification systems like the Sequential Organ Failure Assessment (SOFA) score or the Acute Physiology and Chronic Health Evaluation (APACHE) II score\u0026nbsp;\u003csup\u003e20\u003c/sup\u003e.\u003c/p\u003e\n\u003cp\u003eNormal supervised machine learning classifiers possess distinct characteristics, and their performance is frequently dependent upon the attributes of the datasets being classified. Logistic regression (LR), support vector machine (SVM), decision tree (DT), random forest (RF), and extreme gradient boosting (XGBoost) are popular machine learning techniques; yet, their specific performance on severe pneumonia datasets remains ambiguous. Therefore, this study aimed to accurately, quickly, and comprehensively predict the individual mortality risk of patients with severe pneumonia and improve prognosis by establishing a mortality risk prediction model for severe pneumonia containing the characteristics of TCM using multiple machine learning algorithms.\u003c/p\u003e"},{"header":"Methods","content":"\n\u003ch3\u003eStudy design and population\u003c/h3\u003e\n\u003cp\u003eThis study was conducted to develop a model to predict hospital mortality in patients with severe pneumonia. A retrospective observational study in training set was designed to consecutively enroll patients in wards at the First Affiliated Hospital of Henan University of Chinese Medicine and Henan Provincial Hospital of Chinese Medicine from January 2008 to November 2021. The test set was consistent with patient source for the training set, but prospectively observational study from December 2021 to January 2024. The follow-up of all participants continued until discharge or death. This study was approved by the Ethics Committee of the First Affiliated Hospital of Henan University of Chinese Medicine (No. 2023HL-241-01). All patients or their legal guardians in the test set were asked to sign an informed consent form. However, due to the retrospective nature for the training set, the need to obtain the informed consent was waived by the the Ethics Committee of the First Affiliated Hospital of Henan University of Chinese Medicine. This study complied with the principles defined in the Declaration of Helsinki and the International Conference on Harmonization-Good Clinical Practice guidelines.\u003c/p\u003e\n\u003ch3\u003eInclusion and exclusion criteria\u003c/h3\u003e\n\u003cp\u003eThe inclusion criteria for the training set were: (1) Participants must have a diagnosis of severe pneumonia in accordance with the guidelines established by the Respiratory Society of the Chinese Medical Association \u003csup\u003e\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e\u003c/sup\u003eor the Infectious Disease Society of America/American Thoracic Society \u003csup\u003e\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e\u003c/sup\u003e; (2) The diagnosis of TCM syndrome must adhere to the Traditional Chinese Medicine Diagnosis and Treatment Guidelines for Community-Acquired Pneumonia (2018 Revised Edition) published by the Chinese Medical Association \u003csup\u003e\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e\u003c/sup\u003e; (3) There were no restrictions regarding the gender or comorbidities of the patients, except they had to be 18 years of age or older. The exclusion criteria were: (1) Numerous missing clinical data; (2) A hospital stay of fewer than 3 days.\u003c/p\u003e \u003cp\u003eThe inclusion criteria for the test set were: (1) Participants must be diagnosed with severe pneumonia in accordance with the guidelines of the Respiratory Society of the Chinese Medical Association \u003csup\u003e\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e\u003c/sup\u003e or the Infectious Disease Society of America/American Thoracic Society \u003csup\u003e\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e\u003c/sup\u003e and recruited within three days; (2) There were no restrictions regarding gender or comorbidities, provided participants were 18 years or older; (3) All patients, or their legal representatives in cases where they were unable to provide consent, were required to sign an informed consent form. Besides, individuals with dementia and other mental disorders were excluded.\u003c/p\u003e \u003cp\u003eWe excluded patients with clearly diagnosed fungal and viral pneumonia, including severe Influenza A (H1N1), severe acute respiratory syndrome (SARS), or coronavirus disease 2019 (COVID-19) from both the training and test sets to improve homogeneity.\u003c/p\u003e \u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003eOutcome definition\u003c/h2\u003e \u003cp\u003eThe prediction outcome of this study was the probability of in-hospital mortality, defined as deaths during the current hospitalization period, including within one day after discharge.\u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eFeatures extraction\u003c/h3\u003e\n\u003cp\u003eDemographic characteristics, clinical manifestations, admission risk factors, comorbidities, complications, laboratory results, treatment during hospitalization, and other variables, totaling 115, were as candidates that affect mortality in severe pneumonia. Details were presented 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\u003eThe detailed features of collection\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"3\"\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 \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eItem\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eFeature\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDemographic characteristics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eage, gender, nationality, and solar term\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eClinical manifestations upon admission\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003ebody temperature, respiratory rate, heart rate, systolic and diastolic blood pressure\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRisk factors upon admission\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003ehistory of allergies, smoking, alcohol consumption, fracture, surgery, long-term bed rest, hospitalization within 90 days, ICU admission within 90 days, intravenous antibiotics within 30 days, dialysis within 30 days\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eComorbidities\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003ehypertension, diabetes, chronic bronchitis, chronic obstructive pulmonary disease (COPD), pulmonary fibrosis, bronchiectasis, asthma, old pulmonary tuberculosis, pulmonary abscess, pulmonary heart disease, arrhythmia, cardiac insufficiency, chronic heart failure, parkinson\u0026rsquo;s disease, cerebral infarction, hematencephalon, chronic gastritis, gastrointestinal bleeding, chronic viral hepatitis, liver cirrhosis, chronic renal insufficiency, chronic renal failure, cancer, lumbar disease, and neck disease\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eComplications\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eacid base disturbance, electrolyte imbalance, anemia, hypoproteinemia, acute heart failure, acute myocardial infarction, acute kidney injury, acute liver injury, hypovolemic shock, septic shock, cardiac shock, and pleural effusion\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLaboratory results\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003ewhite blood cell (WBC) count, red blood cell (RBC) count, hemoglobin, hematokrit, platelet count, neutrophilic granulocyte percentage (NEUT%), lymphocyte percentage (LY%), CRP, procalcitonin (PCT), total bilirubin, total protein, albumin, aspartate aminotransferase (AST), alanine amiotransferase (ALT), blood urea nitrogen (BUN), serum creatinine (Scr), potassium, sodium, troponin, myohemoglobin, prothrombin time (PT), activated partial thromboplastin time (APTT), fibrinogen, D-dimer, brain natriuretic peptide (BNP), arterial blood PH, arterial partial pressure of oxygen (PaO\u003csub\u003e2\u003c/sub\u003e), arterial partial pressure of carbon dioxide (PaCO\u003csub\u003e2\u003c/sub\u003e), and arterial oxygenation index (PaO\u003csub\u003e2\u003c/sub\u003e/FiO\u003csub\u003e2\u003c/sub\u003e)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003eTreatment during hospitalization\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003econventional medicine\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eglucocorticoids, number of antibiotics\u0026thinsp;\u0026ge;\u0026thinsp;3, beta-lactam antibiotics, quinolone antibiotics, aminoglycoside antibiotics, macrolide antibiotics, tetracycline antibiotics\u003c/p\u003e \u003cp\u003esulfonamide antibiotics, antifungal drug, immunosuppressant\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003econventional operation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003efiber bronchoscope, transfusion, hemodialysis, extracorporeal membrane oxygenation (ECMO), tracheotomy, retention catheterization, gastric intubation, deep vein catheterization, days of nasal tube oxygen, mask oxygen days, non-invasive mechanical ventilation, invasive mechanical ventilation, and mechanical ventilation\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTCM or TCM appropriate technology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eoral Chinese herbal decoction, Chinese patent medicine injection, TCM appropriate technology\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOthers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eTCM syndrome, multi-drug resistant bacterial infection, total hospitalization days, days of ICU stay\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e\n\u003ch3\u003eMissing data handling\u003c/h3\u003e\n\u003cp\u003eInvestigated and confirmed outliers and missing numbers in the original electronic medical records database. If verification or supplementation was not possible, consider the outlier as a missing value for processing. Variables with missing data over 25% were removed, while multiple imputation would be employed for those within 25%.\u003c/p\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003eStatistical analysis\u003c/h2\u003e \u003cp\u003eEvery statistical analysis and calculations were employed SPSS 26.0 or R 4.3.2 software. The categorical variables expressed as total numbers and percentages, and the χ2 test or Fisher exact test (expected frequency\u0026thinsp;\u0026lt;\u0026thinsp;10) was employed to compare group differences. The normality test was performed on all continuous variables to ascertain if the data adhered to a normal distribution, mostly using the Shapiro Wilk or Kolmogorov Smirnov tests in conjunction with histograms. If the data adhered to a normal distribution, represented as mean (\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:\\stackrel{-}{x}\\)\u003c/span\u003e\u003c/span\u003e)\u0026thinsp;\u0026plusmn;\u0026thinsp;standard deviation (SD), an t-test was employed to assess group differences; conversely, it was denoted by the median and interquartile range (IQR), and applied the Wilcoxon rank sum test.\u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eFeatures selection\u003c/h3\u003e\n\u003cp\u003ePatients with severe pneumonia were categorized into non-survivor and survivor groups based on in-hospital mortality, and characteristics were presented and compared between the groups. The 115 features collected from the training set underwent statistical analysis to identify variables with significant differences between the non-survivor and survivor groups. Additionally, to prevent overfitting, the Least Absolute Shrinkage and Selection Operator (LASSO) using the glmnet package in R 4.3.2 software was employed with 10-fold cross-validation to identify and refine candidate predictors \u003csup\u003e\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e\u003c/sup\u003e. The simplest subset of predictive factors was chosen to identify the independent features for inclusion in the in-hospital mortality risk prediction model for severe pneumonia.\u003c/p\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003eModel development and performance evaluation\u003c/h2\u003e \u003cp\u003eFive machine learning algorithms were employed to develop predictive models: LR, SVM, DT, RF, and XGBoost. The corresponding software packages utilized were glm, e1071, rpart, randomForest, and xgboost, all implemented in R version 4.3.2. The discrimination of each model was assessed using the area under the receiver operating characteristic curve (AUROC) and confusion matrix. Besides, DeLong test was used to compare AUC values and further evaluate the differences in predictive performance between models. The calibration curve assessed the calibration; furthermore, to test the clinical applicability for decision-making by estimating the net benefit at various threshold probabilities, decision curve analysis (DCA) was conducted \u003csup\u003e\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003c/div\u003e"},{"header":"Results","content":"\u003cdiv id=\"Sec10\" class=\"Section2\"\u003e \u003ch2\u003eBasic Features\u003c/h2\u003e \u003cp\u003eA total of 226 adult patients diagnosed with severe pneumonia were included into the final training set for this study, while 97 in the test set. The in-hospital mortality for severe pneumonia was 23.82% in the training set and 29.89% in the test set. No significant difference in mortality was seen between the training and test sets (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026gt;\u0026thinsp;0.05). Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e summarized the comparisons of demographic characteristics, clinical manifestations at admission, risk factors before admission, comorbidities, complications, laboratory results, treatment during hospitalization, and other factors between non-survivors and survivors in the training set. In the training set, there were significant statistical differences between the non-survivors and survivors in a total of 38 factors including age, TCM syndrome, risk factors before admission of fracture history, long-term bed rest history, and intravenous antibiotics within 30 days, comorbidities for cerebral infarction, cardiac insufficiency, gastrointestinal bleeding, and cancer, complications for electrolyte imbalance, anemia, hypoproteinemia, pleural effusion, and septic shock, laboratory results for hematokrit, NEUT%, PCT, total protein, albumin, BUN, Scr, troponin, myohemoglobin, fibrinogen, D-dimer, and arterial blood PH, as well as antifungal drug, transfusion, tracheotomy, retention catheterization, gastric intubation, deep vein catheterization, days of nasal tube oxygen, days of invasive mechanical ventilation, days of mechanical ventilation, oral Chinese herbal decoctions, TCM syndrome, total hospitalization days, days of ICU stay (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05), which might be the potential risk factors for death in patients with severe pneumonia.\u003c/p\u003e \u003cp\u003eThe comparison of features between the training set and the test set was presented in Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e. The training set mainly occurred during the Lesser Cold, Greater Cold, Grain in Beard, and Winter Solstice solar periods, whereas the test set was primarily linked with the Winter Solstice and Lesser Cold. The distribution between the two datasets was statistically significant (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.034). In the training set, the history of alcohol consumption, the presence of pleural effusion comorbidity, the use of three or more antibiotics, the frequency of quinolone antibiotics, as well as hematocrit, ALT, and D-dimer levels, and the duration of mask oxygen therapy were all significantly raised compared to the test set (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05). The comorbidity of gastrointestinal bleeding and the levels of PCT, myohemoglobin, and PaO\u003csub\u003e2\u003c/sub\u003e were considerably reduced compared to the test set (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05). No substantial difference was observed in other features (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026gt;\u0026thinsp;0.05).\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\u003eFeatures comparison between the non-survivors and the survivors for severe pneumonia patients in the training set\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\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 \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFeature\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNon-survivors\u003c/p\u003e \u003cp\u003e(\u003cem\u003en\u003c/em\u003e\u0026thinsp;=\u0026thinsp;64)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eSurvivors\u003c/p\u003e \u003cp\u003e(\u003cem\u003en\u003c/em\u003e\u0026thinsp;=\u0026thinsp;162)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cem\u003eP value\u003c/em\u003e\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eAge\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e78.5 (69.25\u0026ndash;85.75)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e70.5 (58.75\u0026ndash;79.25)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMale\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e44 (68.75%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e114 (70.37%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.938\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eNationalitiy\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 \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHan\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e64 (100.00%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e160 (98.77%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eothers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0 (0.00%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2 (1.23%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eSolar term\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 \u003cp\u003e0.319\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLesser Cold\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (3.13%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e14 (8.64%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGreater Cold\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (3.13%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e14 (8.64%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ethe Beginning of Spring\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (3.13%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7 (4.32%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRain Water\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (3.13%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e8 (4.94%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eInsects awaken\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3 (4.69%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e6 (3.70%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ethe Spring Equinox\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (3.13%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4 (2.47%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePure Brightness\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1 (1.56%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e6 (3.70%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGrain Rain\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3 (4.69%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7 (4.32%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ethe Beginning of Summer\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1 (1.56%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e6 (3.70%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLesser Fullness of Grain\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1 (1.56%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4 (2.47%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGrain in Beard\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e6 (9.38%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e10 (6.17%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ethe Summer Solstice\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3 (4.69%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3 (1.85%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLesser Heat\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (3.13%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e9 (5.56%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGreater Heat\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3 (4.69%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e8 (4.94%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ethe Beginning of Autumn\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3 (4.69%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3 (1.85%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ethe End of Heat\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (3.13%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e5 (3.09%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eWhite Dew\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0 (0.00%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e5 (3.09%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ethe Autumn Equinox\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e7 (10.94%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4 (2.47%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCold Dew\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (3.13%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e6 (3.70%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFrost\u0026rsquo;s Descent\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (3.13%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e6 (3.70%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ethe Beginning of Winter\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e4 (6.25%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7 (4.32%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLesser Snow\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0 (0.00%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7 (4.32%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGreater Snow\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e4 (6.25%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e6 (3.70%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ethe Winter Solstice\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e7 (10.94%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7 (4.32%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\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 \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBody temperature (℃)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e37.05 (36.5\u0026ndash;38)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e36.9 (36.5\u0026ndash;38.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.903\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRespiratory rate (breaths/min)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e22.5 (20\u0026ndash;30)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e21 (20\u0026ndash;25)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.301\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHeart rate (beats/min)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e100.5 (84.25-116.75)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e95.5 (80\u0026ndash;112)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.385\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSystolic pressure (mmHg)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e126 (108.5-145.75)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e126 (116\u0026ndash;140)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.779\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDiastolic pressure (mmHg)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e76 (65\u0026ndash;84)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e77 (70\u0026ndash;84)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.363\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eRisk factors before admission\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAllergic history\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e8 (12.50%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e19 (11.73%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSmoking history\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e10 (15.63%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e36 (22.22%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.281\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAlcohol consumption history\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e7 (10.94%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e28 (17.28%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.308\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFracture history\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e12 (18.75%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e13 (8.02%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.032*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSurgery history\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e28 (43.75%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e55 (33.95%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.220\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLong-term bed rest history\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e35 (54.69%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e62 (38.27%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.026*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHospitalization within 90 days\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e38 (59.38%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e99 (61.11%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.880\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eICU admission within 90 days\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e7 (10.94%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e34 (20.99%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.087\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eIntravenous antibiotics within 30 days\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e23 (35.94%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e89 (54.94%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.010*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDialysis within 30 days\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0 (0.00%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7 (4.32%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.207\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 \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\u003e36 (56.25%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e81 (50.00%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.461\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\u003e20 (31.25%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e48 (29.63%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.872\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eChronic bronchitis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e10 (15.63%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e18 (11.11%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.374\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\u003e12 (18.75%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e21 (12.96%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.298\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePulmonary fibrosis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e8 (12.50%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e19 (11.73%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBronchiectasis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1 (1.56%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e6 (3.70%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.681\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\u003e1 (1.56%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e9 (5.56%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.339\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOld pulmonary tuberculosis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1 (1.56%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e8 (4.94%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.428\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePulmonary abscess\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0 (0.00%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2 (1.23%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePulmonary heart disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (3.12%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e8 (4.94%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.812\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eArrhythmia\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e21 (32.81%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e33 (20.37%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.057\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCardiac insufficiency\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e12 (18.75%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e10 (6.17%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.006*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eChronic heart failure\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e10 (15.63%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e13 (8.02%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.140\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eParkinson\u0026rsquo;s disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3 (4.69%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7 (4.32%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCerebral infarction\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e35 (54.69%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e52 (32.10%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.002*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHematencephalon\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e8 (12.50%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e15 (9.26%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.626\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eChronic gastritis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e5 (7.81%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7 (4.32%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.468\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGastrointestinal bleeding\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e6 (9.38%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2 (1.23%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.010*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eChronic viral hepatitis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (3.12%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e10 (6.17%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.554\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLiver cirrhosis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1 (1.56%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e6 (3.70%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.681\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eChronic renal insufficiency\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e4 (6.25%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e5 (3.09%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.473\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eChronic renal failure\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (3.12%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e6 (3.70%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCancer\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e9 (14.06%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e5 (3.09%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.005*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLumbar disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e6 (9.38%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e9 (5.56%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.458\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNeck disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (3.12%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4 (2.47%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.000\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 \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAcid base disturbance\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e36 (56.25%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e88 (54.32%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.882\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eElectrolyte imbalance\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e48 (75.00%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e97 (59.88%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.045*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAnemia\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e46 (71.88%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e89 (54.94%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.024*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHypoproteinemia\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e59 (92.19%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e130 (80.25%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.029*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePleural effusion\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e62 (96.88%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e134 (82.72%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.005*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAcute myocardial infarction\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3 (4.69%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4 (2.47%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.659\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAcute heart failure\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e9 (14.06%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e10 (6.17%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.065\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAcute kidney injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e12 (18.75%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7 (4.32%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.389\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAcute liver injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e7 (10.94%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e13 (8.02%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.603\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHypovolemic shock\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (3.12%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2 (1.23%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.681\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSeptic shock\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e18 (28.13%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e11 (6.79%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCardiac shock\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (3.12%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4 (2.47%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eLaboratory results\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 \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eWBC (\u0026times;10\u003csup\u003e9\u003c/sup\u003e/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e9.85 (6.66\u0026ndash;15.71)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e8.6 (6.68\u0026ndash;12.03)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.187\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRBC (\u0026times;10\u0026sup1;\u0026sup2;/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3.68 (3.1\u0026ndash;4.32)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3.91 (3.41\u0026ndash;4.43)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.087\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\u003e111 (94.25\u0026ndash;129.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e119 (101.75-134.25)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.061\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHematokrit (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e33.9 (28.75\u0026ndash;38.38)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e36.6 (31.35\u0026ndash;40.73)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.021*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePlatelet count (\u0026times;10\u003csup\u003e9\u003c/sup\u003e/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e184.5 (112\u0026ndash;236)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e191 (134.75\u0026ndash;249.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.214\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNEUT%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e88.7 (82.95\u0026ndash;93.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e84.2 (76.28\u0026ndash;89.83)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.004*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLY%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e7.55 (3.87\u0026ndash;12.38)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e9.85 (5.93\u0026ndash;15.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.076\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\u003e84.11 (35.5-161.91)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e78.79 (30.92\u0026ndash;161)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.449\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePCT (\u0026micro;g/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.62 (0.36\u0026ndash;2.95)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.35 (0.1\u0026ndash;0.77)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTotal bilirubin (\u0026micro;mol/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e15.15 (9.93\u0026ndash;24.43)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e12.85 (9.3\u0026ndash;18.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.100\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTotal protein (g/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e56.71\u0026thinsp;\u0026plusmn;\u0026thinsp;11.19\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e60.44\u0026thinsp;\u0026plusmn;\u0026thinsp;8.88\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.019*\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\u003e29.75\u0026thinsp;\u0026plusmn;\u0026thinsp;6.3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e32.19\u0026thinsp;\u0026plusmn;\u0026thinsp;4.93\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.007*\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\u003e22.05 (13.25\u0026ndash;35.68)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e22.1 (13.45\u0026ndash;39.53)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.920\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\u003e30.25 (19.28\u0026ndash;58.25)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e26.25 (16.98\u0026ndash;44.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.281\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\u003e11.85 (7.4-17.52)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e6.48 (4.63\u0026ndash;10.38)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eScr (\u0026micro;mol/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e81.75 (56-134.58)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e65.5 (50.15\u0026ndash;94.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.021*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePotassium (mmol/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e4.2\u0026thinsp;\u0026plusmn;\u0026thinsp;0.76\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4.15\u0026thinsp;\u0026plusmn;\u0026thinsp;0.75\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.654\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSodium (mmol/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e137.2 (132.1-141.78)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e137.6 (134.88\u0026ndash;141)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.619\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTroponin (ng/ml)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.05 (0.05\u0026ndash;0.19)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.05 (0.01\u0026ndash;0.07)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMyohemoglobin (ng/ml)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e40.74 (40.74-78)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e40.74 (21.1-69.83)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.022*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePT (s)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e13.75 (12.2-15.58)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e12.95 (11.7-14.53)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.051\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAPTT (s)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e34.55 (29.3-40.25)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e33.05 (28.48\u0026ndash;39.28)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.253\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFibrinogen (g/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e4.62 (3.03\u0026ndash;5.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e5.37 (4.1\u0026ndash;6.56)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.013*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eD-dimer (\u0026micro;g/ml)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2.93 (1.79\u0026ndash;5.06)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2.11 (1.02\u0026ndash;3.79)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.007*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBNP (pg/ml)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e190 (80.16-578.63)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e245 (83.96\u0026ndash;881.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.392\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eArterial blood PH\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e7.43 (7.36\u0026ndash;7.46)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7.44 (7.42\u0026ndash;7.48)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.008*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePaO\u003csub\u003e2\u003c/sub\u003e (mmHg)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e61.4 (56-83.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e61.4 (54-70.08)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.174\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePaCO\u003csub\u003e2\u003c/sub\u003e (mmHg)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e32.95 (25.38\u0026ndash;37.95)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e32.95 (29.95\u0026ndash;40.08)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.196\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePaO\u003csub\u003e2\u003c/sub\u003e/FiO\u003csub\u003e2\u003c/sub\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e229.5 (171.75-261.75)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e229.5 (193.75\u0026ndash;276)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.101\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eApplication of conventional medicine\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 \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGlucocorticoids\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e36 (56.25%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e91 (56.17%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNumber of antibiotics\u0026thinsp;\u0026ge;\u0026thinsp;3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e54 (84.38%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e117 (72.22%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.055\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBeta-lactam antibiotics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e64 (100.00%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e158 (97.53%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.479\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eQuinolone antibiotics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e41 (64.06%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e122 (75.31%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.101\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAminoglycoside antibiotics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e9 (14.06%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e17 (10.49%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.490\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMacrolide antibiotics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e12 (18.75%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e25 (15.43%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.553\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTetracycline antibiotics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e16 (25.00%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e24 (14.81%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.083\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSulfonamide antibiotics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0 (0.00%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1 (0.62%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAntifungal drug\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e27 (42.19%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e45 (27.78%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.041*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eImmunosuppressant\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e4 (6.25%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e5 (3.09%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.473\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eConventional operation\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 \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFiber bronchoscope\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e31 (48.44%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e76 (46.91%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.883\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTransfusion\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e21 (32.81%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e31 (19.14%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.035*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHemodialysis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e4 (6.25%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e8 (4.94%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.947\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eECMO\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1 (1.56%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1 (0.62%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.487\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTracheotomy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3 (4.69%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e30 (18.52%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.008*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRetention catheterization\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e56 (87.50%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e73 (45.06%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGastric intubation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e45 (70.31%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e78 (48.15%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.003*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDeep vein catheterization\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e39 (60.94%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e75 (46.30%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.047*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDays of nasal tube oxygen\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0 (0-8.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4 (0\u0026ndash;14)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.019*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDays of mask oxygen days\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0 (0\u0026ndash;1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.095\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDays of non-invasive mechanical ventilation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0 (0\u0026ndash;3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0 (0\u0026ndash;2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.098\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDays of invasive mechanical ventilation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.5 (0\u0026ndash;8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0 (0\u0026ndash;4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDays of mechanical ventilation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e6.5 (1\u0026ndash;11)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0 (0\u0026ndash;11)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.005*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eTCM or TCM appropriate technology\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 \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOral Chinese herbal decoction\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e27 (42.19%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e139 (85.80%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eChinese patent medicine injection\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e55 (85.94%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e126 (77.78%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.198\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTCM appropriate technology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e54 (84.38%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e136 (83.95%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eTCM syndrome\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 \u003cp\u003e\u0026lt;\u0026thinsp;0.001*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePhlegm-heat obstructing lung syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e13 (20.31%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e65 (40.12%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePhlegm turbidity obstructing lung syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e17 (26.56%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e26 (16.05%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDeficiency of both qi and yin syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e9 (14.06%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e14 (8.64%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLung-spleen qi deficiency syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e6 (9.38%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e10 (6.17%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLung-spleen qi deficiency combined with phlegm turbidity obstructing lung syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (3.13%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e11 (6.79%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePhlegm turbidity obstructing lung combined with stagnation of blood syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (3.13%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7 (4.32%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDeficiency of both qi and yin combined with phlegm turbidity obstructing lung syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1 (1.56%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7 (4.32%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePathogenic qi falling into and prostration syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e6 (9.38%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1 (0.62%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eInvasion of pericardium by heat syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0 (0.00%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e6 (3.70%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePhlegm-heat obstructing lung combined with stagnation of blood syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1 (1.56%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e5 (3.09%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDeficiency of both qi and yin combined with phlegm-heat obstructing lung syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (3.13%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4 (2.47%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLung-spleen qi deficiency combined with phlegm-heat obstructing lung syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1 (1.56%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4 (2.47%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLung-spleen qi deficiency combined with stagnation of blood syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (3.13%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2 (1.23%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eStagnation of blood syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1 (1.56%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0 (0.00%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDeficiency of both qi and yin combined with stagnation of blood syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1 (1.56%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0 (0.00%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eOthers\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 \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMulti-drug resistant bacterial infection\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e20 (31.25%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e49 (30.25%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTotal hospitalization days\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e12 (8.25-23)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e17 (13\u0026ndash;27)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.001*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDays of ICU stay\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e4 (0-10.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0 (0-4.25)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001*\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\u003eFeatures comparison between the training and test set\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\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 \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFeature\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTraining Set\u003c/p\u003e \u003cp\u003e(\u003cem\u003en\u003c/em\u003e\u0026thinsp;=\u0026thinsp;226)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eTest Set\u003c/p\u003e \u003cp\u003e(\u003cem\u003en\u003c/em\u003e\u0026thinsp;=\u0026thinsp;97)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cem\u003eP value\u003c/em\u003e\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eAge\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e72 (63\u0026ndash;82)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e76 (65\u0026ndash;84)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.155\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMale\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e158 (69.91%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e60 (61.86%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.157\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eNationalitiy\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 \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHan\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e224 (99.12%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e96 (98.97%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eothers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (0.88%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1 (1.03%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eSolar term\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 \u003cp\u003e0.034*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLesser Cold\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e16 (7.08%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e11 (11.34%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGreater Cold\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e16 (7.08%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3 (3.09%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ethe Beginning of Spring\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e9 (3.98%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7 (7.22%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRain Water\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e10 (4.42%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4 (4.12%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eInsects awaken\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e9 (3.98%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1 (1.03%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ethe Spring Equinox\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e6 (2.65%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7 (7.22%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePure Brightness\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e7 (3.10%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3 (3.09%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGrain Rain\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e10 (4.42%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e5 (5.15%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ethe Beginning of Summer\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e7 (3.10%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e6 (6.19%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLesser Fullness of Grain\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e5 (2.21%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e5 (5.15%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGrain in Beard\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e16 (7.08%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4 (4.12%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ethe Summer Solstice\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e6 (2.65%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2 (2.06%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLesser Heat\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e11 (4.87%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2 (2.06%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGreater Heat\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e11 (4.87%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2 (2.06%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ethe Beginning of Autumn\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e6 (2.65%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4 (4.12%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ethe End of Heat\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e7 (3.10%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7 (7.22%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eWhite Dew\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e5 (2.21%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1 (1.03%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ethe Autumn Equinox\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e11 (4.87%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4 (4.12%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCold Dew\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e8 (3.54%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0 (0.00%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFrost\u0026rsquo;s Descent\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e8 (3.54%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1 (1.03%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ethe Beginning of Winter\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e11 (4.87%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0 (0.00%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLesser Snow\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e7 (3.10%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1 (1.03%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGreater Snow\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e10 (4.42%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4 (4.12%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ethe Winter Solstice\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e14 (6.19%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e13 (13.40%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\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 \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBody temperature (℃)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e36.9 (36.5-38.23)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e36.8 (36.5\u0026ndash;37.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.226\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRespiratory rate (breaths/min)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e22 (20\u0026ndash;27)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e22 (20\u0026ndash;26)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.770\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHeart rate (beats/min)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e97.5 (80\u0026ndash;113)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e89 (80\u0026ndash;107)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.330\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSystolic pressure (mmHg)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e126 (114\u0026ndash;140)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e123 (113.5-135.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.180\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDiastolic pressure (mmHg)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e76 (69\u0026ndash;84)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e75 (66\u0026ndash;81)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.224\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eRisk factors before admission\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAllergic history\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e27 (11.95%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e17 (17.53%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.180\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSmoking history\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e46 (20.35%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e14 (14.43%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.210\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAlcohol consumption history\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e35 (15.49%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7 (7.22%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.043*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFracture history\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e25 (11.06%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e11 (11.34%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.942\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSurgery history\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e83 (36.73%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e30 (30.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.317\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLong-term bed rest history\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e97 (42.92%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e46 (47.42%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.455\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHospitalization within 90 days\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e137 (60.62%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e60 (61.86%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.835\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eICU admission within 90 days\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e41 (18.14%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e17 (17.53%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.895\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eIntravenous antibiotics within 30 days\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e112 (49.56%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e58 (59.79%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.091\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDialysis within 30 days\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e7 (3.10%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3 (3.09%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.000\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 \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\u003e117 (51.77%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e50 (51.55%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.971\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\u003e68 (30.09%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e33 (34.02%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.971\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eChronic bronchitis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e28 (12.39%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4 (4.12%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.023\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\u003e33 (14.60%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e12 (12.37%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.596\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePulmonary fibrosis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e27 (11.95%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e16 (16.49%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.270\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBronchiectasis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e7 (3.10%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3 (3.09%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.000\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\u003e10 (4.42%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1 (1.03%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOld pulmonary tuberculosis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e9 (3.98%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2 (2.06%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.591\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePulmonary abscess\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (0.88%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0 (0.00%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePulmonary heart disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e10 (4.42%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1 (1.03%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.227\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eArrhythmia\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e54 (23.89%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e33 (34.02%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.081\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCardiac insufficiency\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e22 (9.73%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e14 (14.43%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.219\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eChronic heart failure\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e23 (10.18%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e14 (14.43%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.271\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eParkinson\u0026rsquo;s disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e10 (4.42%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4 (4.12%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCerebral infarction\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e87 (38.50%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e35 (36.08%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.682\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHematencephalon\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e23 (10.18%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e8 (8.25%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.589\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eChronic gastritis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e12 (5.31%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3 (3.09%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.562\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGastrointestinal bleeding\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e8 (3.54%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e9 (9.28%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.034*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eChronic viral hepatitis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e12 (5.31%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3 (3.09%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.562\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLiver cirrhosis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e7 (3.10%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2 (2.06%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.881\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eChronic renal insufficiency\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e9 (3.98%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e8 (8.25%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.116\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eChronic renal failure\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e8 (3.54%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7 (7.22%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.250\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCancer\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e14 (6.19%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e9 (9.28%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.323\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLumbar disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e15 (6.64%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2 (2.06%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.091\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNeck disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e6 (2.65%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3 (3.09%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.000\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 \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAcid base disturbance\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e124 (54.87%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e56 (57.73%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.635\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eElectrolyte imbalance\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e145 (64.16%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e68 (70.10%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.301\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAnemia\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e135 (59.73%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e66 (68.04%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.158\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHypoproteinemia\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e189 (83.63%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e89 (91.75%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.053\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePleural effusion\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e196 (86.73%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e64 (65.98%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAcute myocardial infarction\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e7 (3.10%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3 (3.09%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAcute heart failure\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e19 (8.41%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7 (7.22%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.718\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAcute kidney injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e19 (8.41%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e8 (8.25%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.962\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAcute liver injury\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e20 (8.85%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e12 (12.37%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.962\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHypovolemic shock\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e4 (1.77%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2 (2.06%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSeptic shock\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e29 (12.83%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e16 (16.49%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.384\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCardiac shock\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e6 (2.65%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0 (0.00%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.242\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eLaboratory results\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 \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eWBC (\u0026times;10\u003csup\u003e9\u003c/sup\u003e/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e8.8 (6.68\u0026ndash;12.58)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e9.7 (6.89\u0026ndash;14.09)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.299\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRBC (\u0026times;10\u0026sup1;\u0026sup2;/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3.82\u0026thinsp;\u0026plusmn;\u0026thinsp;0.83\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3.62\u0026thinsp;\u0026plusmn;\u0026thinsp;0.88\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.058\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\u003e117 (99.75-132.25)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e112 (91.5-126.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.163\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHematokrit (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e36 (30.7\u0026ndash;40.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e33.3 (28.15\u0026ndash;38.25)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.011*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePlatelet count (\u0026times;10\u003csup\u003e9\u003c/sup\u003e/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e191 (133\u0026ndash;246)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e206 (131\u0026ndash;275)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.161\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNEUT%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e86.15 (78.23\u0026ndash;90.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e85.9 (77.7\u0026ndash;90.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.963\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLY%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e9.1 (5.08\u0026ndash;14.64)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e8.4 (5.05\u0026ndash;15.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.961\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\u003e81.21 (33.03\u0026ndash;161)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e83.2 (30.88\u0026ndash;157.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.953\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePCT (\u0026micro;g/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.36 (0.12\u0026ndash;1.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.4 (0.2\u0026ndash;1.92)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.022*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTotal bilirubin (\u0026micro;mol/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e13.2 (9.38\u0026ndash;19.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e12.3 (7.7\u0026ndash;18.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.156\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTotal protein (g/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e59.38\u0026thinsp;\u0026plusmn;\u0026thinsp;9.71\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e57.84\u0026thinsp;\u0026plusmn;\u0026thinsp;7.49\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.123\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\u003e31.5\u0026thinsp;\u0026plusmn;\u0026thinsp;5.45\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e30.38\u0026thinsp;\u0026plusmn;\u0026thinsp;4.95\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.082\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\u003e22.1 (13.45\u0026ndash;37.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e17 (11.15\u0026ndash;27.25)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.017*\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\u003e26.9 (17.38\u0026ndash;44.55)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e24 (17.7-46.45)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.313\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\u003e7.39 (5.09\u0026ndash;12.91)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e9.22 (5.06\u0026ndash;15.56)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.209\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\u003e70.55 (52.05-106.33)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e60 (46.05-109.55)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.177\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePotassium (mmol/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e4.17\u0026thinsp;\u0026plusmn;\u0026thinsp;0.75\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4.07\u0026thinsp;\u0026plusmn;\u0026thinsp;0.68\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.275\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSodium (mmol/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e137.6 (134\u0026ndash;141)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e137 (134-141.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.866\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTroponin (ng/ml)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.05 (0.02\u0026ndash;0.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.05 (0.03\u0026ndash;0.09)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.758\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMyohemoglobin (ng/ml)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e40.74 (28.38\u0026ndash;69.83)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e45.7 (44.7\u0026ndash;73.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.000*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePT (s)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e13.2 (11.9\u0026ndash;14.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e13.60 (11.95\u0026ndash;15.40)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.312\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAPTT (s)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e33.20 (28.70\u0026ndash;39.70)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e31.90 (28.61\u0026ndash;39.25)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.393\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFibrinogen (g/L)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e5.16 (3.79\u0026ndash;6.49)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e5.19 (3.81\u0026ndash;6.55)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.735\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eD-dimer (\u0026micro;g/ml)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2.29 (1.18\u0026ndash;4.18)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.87 (1.04\u0026ndash;2.77)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.009*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBNP (pg/ml)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e223 (81.57\u0026ndash;814.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e223 (119-635.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.332\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eArterial blood PH\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e7.44 (7.4\u0026ndash;7.48)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7.45 (7.38\u0026ndash;7.48)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.364\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePaO\u003csub\u003e2\u003c/sub\u003e (mmHg)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e61.4 (55-75.65)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e62.7 (58.9\u0026ndash;80)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.033*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePaCO\u003csub\u003e2\u003c/sub\u003e (mmHg)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e32.95 (28.93\u0026ndash;39.08)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e33 (31.1\u0026ndash;36.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.374\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePaO\u003csub\u003e2\u003c/sub\u003e/FiO\u003csub\u003e2\u003c/sub\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e229.5 (190.25\u0026ndash;270)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e230 (145.5\u0026ndash;282)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.931\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eApplication of conventional medicine\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 \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGlucocorticoids\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e127 (56.19%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e58 (59.79%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.549\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNumber of antibiotics\u0026thinsp;\u0026ge;\u0026thinsp;3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e171 (75.66%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e58 (59.79%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.004*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBeta-lactam antibiotics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e222 (98.23%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e92 (94.85%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.185\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eQuinolone antibiotics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e163 (72.12%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e44 (45.36%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAminoglycoside antibiotics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e26 (11.50%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e8 (8.25%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.382\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMacrolide antibiotics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e37 (16.37%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e15 (15.46%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.839\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTetracycline antibiotics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e40 (17.70%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e22 (22.68%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.297\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSulfonamide antibiotics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1 (0.44%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0 (0.00%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAntifungal drug\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e72 (31.86%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e37 (38.14%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.273\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eImmunosuppressant\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e9 (3.98%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2 (2.06%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.591\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eConventional operation\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 \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFiber bronchoscope\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e107 (47.35%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e45 (46.39%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.875\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTransfusion\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e52 (23.01%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e28 (28.87%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.264\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHemodialysis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e12 (5.31%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e9 (9.28%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.185\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eECMO\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (0.88%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1 (1.03%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTracheotomy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e33 (14.60%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e17 (17.53%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.505\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRetention catheterization\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e129 (57.08%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e60 (61.86%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.425\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGastric intubation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e123 (54.42%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e57 (58.76%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.472\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDeep vein catheterization\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e114 (50.44%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e49 (50.52%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.990\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDays of nasal tube oxygen\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (0\u0026ndash;12)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0 (0\u0026ndash;8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.077\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDays of mask oxygen days\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0 (0\u0026ndash;0)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.009*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDays of non-invasive mechanical ventilation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0 (0\u0026ndash;3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0 (0\u0026ndash;2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.505\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDays of invasive mechanical ventilation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0 (0\u0026ndash;7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0 (0\u0026ndash;6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.796\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDays of mechanical ventilation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3 (0\u0026ndash;11)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3 (0\u0026ndash;10)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.871\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eTCM or TCM appropriate technology\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 \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOral Chinese herbal decoction\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e166 (73.45%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e61 (62.89%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.064\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eChinese patent medicine injection\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e181 (80.09%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e84 (86.60%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.162\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTCM appropriate technology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e190 (84.07%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e78 (80.41%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.423\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eTCM syndrome\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 \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePhlegm-heat obstructing lung syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e78 (34.51%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e41 (42.27%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.354\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePhlegm turbidity obstructing lung syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e43 (19.03%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e22 (22.68%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDeficiency of both qi and yin syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e23 (10.18%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e6 (6.19%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLung-spleen qi deficiency syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e16 (7.08%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e11 (11.34%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLung-spleen qi deficiency combined with phlegm turbidity obstructing lung syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e13 (5.75%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3 (3.09%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePhlegm turbidity obstructing lung combined with stagnation of blood syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e9 (3.98%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0 (0.00%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDeficiency of both qi and yin combined with phlegm turbidity obstructing lung syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e8 (3.54%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3 (3.09%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePathogenic qi falling into and prostration syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e7 (3.10%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3 (3.09%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eInvasion of pericardium by heat syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e6 (2.65%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2 (2.06%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePhlegm-heat obstructing lung combined with stagnation of blood syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e6 (2.65%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0 (0.00%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDeficiency of both qi and yin combined with phlegm-heat obstructing lung syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e6 (2.65%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3 (3.09%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLung-spleen qi deficiency combined with phlegm-heat obstructing lung syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e5 (2.21%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1 (1.03%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLung-spleen qi deficiency combined with stagnation of blood syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e4 (1.77%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0 (0.00%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eStagnation of blood syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1 (0.44%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1 (1.03%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDeficiency of both qi and yin combined with stagnation of blood syndrome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1 (0.44%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1 (1.03%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eOthers\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 \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMulti-drug resistant bacterial infection\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e69 (30.53%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e31 (32.96%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.896\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTotal hospitalization days\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e16 (11\u0026ndash;27)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e15 (9.5\u0026ndash;24.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.266\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDays of ICU stay\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0 (0\u0026ndash;7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0 (0\u0026ndash;7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.710\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=\"Sec11\" class=\"Section2\"\u003e \u003ch2\u003eFeatures selection\u003c/h2\u003e \u003cp\u003eThe LASSO regression identified 7 predictors from above 38 possible risk factors for 226 patients in the training set, according to the lambda.1se criterion for predictor selection, which was used for model construction (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e). All of the 7 predictors including age, TCM syndrome (pathogenic qi falling into and prostration syndrome), complication of septic shock, BNU level, tracheotomy application, retention catheterization application, and oral Chinese herbal decoction entered the final LR, SVM, DT, RF and XGBoost models.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec12\" class=\"Section2\"\u003e \u003ch2\u003eModel development, evaluation and comparison\u003c/h2\u003e \u003cdiv id=\"Sec13\" class=\"Section3\"\u003e \u003ch2\u003eDiscrimination\u003c/h2\u003e \u003cp\u003eThe RF model demonstrated superior performance in the training set, attaining an accuracy of 0.982, a recall of 1.000, a precision of 0.941, an F1 score of 0.970, and an AUC of 0.999. The excessive high value of the indicators might be related to the overfitting of this model. The SVM indicators exhibited the lowest values among the five models, with an accuracy of 0.159, recall of 0.156, precision of 0.068, F1 score of 0.095, and AUC of 0.900. Moreover, the AUC of all five prediction models over 0.9, signifying a strong fitting performance in the training set. In the test set, the SVM model showed significantly inferior accuracy, recall, precision, and F1 score compared to other models, yet had the best AUC. The RF model revealed superior performance in accuracy, recall, precision, and F1 score metrics, with an AUC value ranking second only to the SVM model among the five models. Furthermore, the XGBoost model had the third best AUROC (0.853). The predicted value of the XGBoost model exceeded that of the Pneumonia Severity Index (PSI), SOFA, and APACHE II scoring systems, which showed AUC values of 0.808, 0.819, and 0.837, respectively. The comprehensive results of the discrimination among the five models presented in Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e, while the ROC curves are illustrated in Figs.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e and \u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e. The DeLong test showed that there were significant differences in AUC between the RF model and others in the training set, also between the XGBoost and SVM models (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05); but there was no significant difference among the models in the test set (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026gt;\u0026thinsp;0.05). The results of DeLong test illustrated in Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab4\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eComparing the discrimination of the five severe pneumonia hospital mortality prediction models\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"12\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c10\" colnum=\"10\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c11\" colnum=\"11\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c12\" colnum=\"12\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eModel\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"5\" nameend=\"c6\" namest=\"c2\"\u003e \u003cp\u003eTraining Set (\u003cem\u003en\u003c/em\u003e\u0026thinsp;=\u0026thinsp;226)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colspan=\"5\" nameend=\"c12\" namest=\"c8\"\u003e \u003cp\u003eTest Set (\u003cem\u003en\u003c/em\u003e\u0026thinsp;=\u0026thinsp;97)\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAccuracy\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eRecall\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003ePrecision\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eF1 score\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eAUC\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c8\"\u003e \u003cp\u003eAccuracy\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c9\"\u003e \u003cp\u003eRecall\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c10\"\u003e \u003cp\u003ePrecision\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c11\"\u003e \u003cp\u003eF1 score\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c12\"\u003e \u003cp\u003eAUC\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.845\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.844\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.684\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.755\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.904\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e0.732\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.793\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0.535\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003e0.639\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003e0.844\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSVM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.159\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.156\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.068\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.095\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.900\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e0.247\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.103\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0.060\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003e0.076\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003e0.877\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDT\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.854\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.844\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.594\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.697\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.904\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e0.753\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.609\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0.483\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003e0.539\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003e0.802\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.982\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.941\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.970\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.999\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e0.773\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.793\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0.590\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003e0.677\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003e0.855\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eXGBoost\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.788\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.906\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.580\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.707\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.929\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e0.701\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e0.897\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c10\"\u003e \u003cp\u003e0.500\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c11\"\u003e \u003cp\u003e0.642\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c12\"\u003e \u003cp\u003e0.853\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 \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv id=\"Sec14\" class=\"Section2\"\u003e \u003ch2\u003eCalibration\u003c/h2\u003e \u003cp\u003eIn the training set, the DT model exhibited the most optimal calibration, succeeded by XGBoost, LR, RF, and SVM models. In the test set, the calibration performance ranked from highest to lowest as follows: XGBoost, RF, LR, DT, and SVM model (Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec15\" class=\"Section2\"\u003e \u003ch2\u003eClinical practicability\u003c/h2\u003e \u003cp\u003eIn the training set, the net benefit of the RF model exceeded that of the DT, LR, XGBoost, and SVM models as indicated by the DCA. In the test set, the XGBoost model exhibited the highest net benefit, while the SVM model performed the poorest, indicating that the XGBoost model was the most optimal. Moreover, with the exception of the SVM model, DCA curves showed that the other four models demonstrate clinical value (Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e6\u003c/span\u003e).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec16\" class=\"Section2\"\u003e \u003ch2\u003eOptimal model analysis\u003c/h2\u003e \u003cp\u003eIn comparison to the other four models, the XGBoost model demonstrated the third highest AUROC (0.853), along with optimal calibration and clinical applicability. The DCA curve indicated potential clinical benefit in predicting hospital mortality in patients with severe pneumonia. Thus, the XGBoost model emerged as the optimal selection, evaluated comprehensively across the dimensions of discrimination, calibration, and clinical practicability. SHAP values were calculated for the XGBoost prediction model to assess the significance of variables and the validity of internal algorithm. The application of retention catheterization exhibited the highest predictive value across all forecasting horizons, succeeded by the variables of oral Chinese herbal decoction, BUN level, age, application of tracheotomy, complication of septic shock, and TCM syndrome (pathogenic qi falling into and prostration syndrome). Furthermore, raised BUN levels and age, along with complication of septic shock, the application of retention catheterization, and TCM syndrome (pathogenic qi deficiency and prostration syndrome), positively influenced mortality predictions. Conversely, the application of tracheotomy and oral Chinese herbal decoction negatively affected mortality predictions, indicating a tendency toward survival. The SHAP values of the seven predictors in the XGBoost model illustrated in Fig.\u0026nbsp;\u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e7\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e"},{"header":"Discussion","content":"\u003cdiv id=\"Sec18\" class=\"Section2\"\u003e \u003ch2\u003ePrincipal findings\u003c/h2\u003e \u003cp\u003eOur study retrospectively gathered clinical data from 226 patients with severe pneumonia for the training set, of whom 64 died in-hospital, resulting in a mortality of 28.32%, consistent with findings from prior studies \u003csup\u003e\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e\u003c/sup\u003e. The Lasso regression analysis was conducted to identify risk factors associated with severe pneumonia mortality in relation to Chinese and conventional medicine, including age, complication of septic shock, BNU level, TCM syndrome (pathogenic qi falling into and prostration syndrome), application of tracheotomy, retention catheterization, and oral Chinese herbal decoction. The implementation of tracheotomy and the administration of oral Chinese herbal decoction are protective variables influencing the mortality outcomes of patients with severe pneumonia. We constructed and validated models capable of predicting mortality in patients with severe pneumonia using routinely available clinical data, and compared five machine learning algorithms. The XGBoost model is superior to the overall performance of LR, SVM, DT, RF, as well as the scoring systems of PSI, SOFA, and APACHE II. The SHAP method explains the XGBoost model, so enhancing both model performance and clinical interpretability. This model may possess potential utility in personalized surveillance prognosis, facilitating improved therapy schedules and appropriate resource allocation for patients.\u003c/p\u003e \u003cp\u003eMachine learning is characterized by its applicability to various types of datasets, resulting in its widespread utilization. Nonetheless, various algorithms possess distinct benefits, and their capacity and efficacy in problem-solving mostly depend on the characteristics of data aspects and the performance of algorithms. Consequently, evaluating the efficacy of various machine learning algorithms on a particular dataset to identify the ideal model, together with employing feature importance analysis to enhance comprehension of presented features, is highly significant \u003csup\u003e\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e\u003c/sup\u003e. The most significant predictive factor in the optimal XGBoost model is the application of retention catheterization, succeeded by oral Chinese herbal decoction, BUN level, age, tracheotomy application, complication of septic shock, and TCM syndrome (pathogenic qi falling into and prostration syndrome).\u003c/p\u003e \u003cp\u003ePatients with severe pneumonia frequently present with multiple underlying diseases, and those in critical condition often suffer from consciousness disorders, hindering their ability to urinate autonomously; thus, the application of retention catheterization is required. However, this study identified that indwelling catheters are an important risk factor for mortality due to severe pneumonia, corroborating findings from previous studies \u003csup\u003e\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eRecent studies have demonstrated that TCM, when combined with conventional treatment, offers improvements in the management of severe pneumonia \u003csup\u003e\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e\u003c/sup\u003e. Our research showed that a duration of over 5 days of oral Chinese herbal decoction might decrease the mortality risk of severe pneumonia, hence revealing the efficacy of TCM for treating severe pneumonia based on syndrome differentiation.\u003c/p\u003e \u003cp\u003eBUN is a primary end product of protein metabolism in the human body and serves as a crucial indication for assessing kidney function. The lung and kidney exhibit complex connections, both playing crucial organs in regulating acid-base and fluid balance \u003csup\u003e\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e\u003c/sup\u003e. In addition, any impairment to the kidneys can substantially impact the lungs by disturbing normal the pH and fluid distribution balance. Furthermore, the kidneys may promote the progression and regulate of pulmonary illnesses by the production or elimination of mediators. The interaction between the lungs and kidneys highlights their mutual dependence and impact on overall physiological function \u003csup\u003e\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e\u003c/sup\u003e. A study indicated that patients with acute kidney injury and pneumonia exhibited a greater mortality compared to those with either condition alone \u003csup\u003e\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e\u003c/sup\u003e. Furthermore, a diagnostic criterion for severe pneumonia includes BUN levels, signifying a strong association between BUN and disease severity. Our study demonstrates that BUN is a significant risk factor for increased mortality in patients with severe pneumonia, potentially attributable to the relationship between the lung microbiome in these patients and kidney damage \u003csup\u003e\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eWith advancing age, the human immune system experiences various alterations, resulting in diminished capacity to efficiently trigger cellular responses against pathogens. The chemotactic capacity of polymorphonuclear leukocytes in the elderly is weakened, and the microbial uptake and antigen processing capabilities of macrophages are correspondingly reduced \u003csup\u003e\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e\u003c/sup\u003e. Moreover, age-related factors such as chronic comorbidities, alterations in immunological physiology, and malnutrition substantially increase the risk of infection in the elderly \u003csup\u003e\u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e\u003c/sup\u003e. The results of this study indicate that the risk of mortality from severe pneumonia increases with age, which is consistent with previous research findings \u003csup\u003e\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e\u003c/sup\u003e and potentially linked to age-associated chronic disorders and/or diminished immune function \u003csup\u003e\u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eIndividuals with severe pneumonia display a substantial elevation in airway secretions. When accompanied with consciousness problems, severe cerebral infarction, traumatic brain injury, or additional problems, respiratory function becomes impaired, requiring ventilator support. Elderly patients, due to their numerous medical conditions, are susceptible to difficulties such as the accumulation of airway secretions, respiratory obstruction, and throat injury during prolonged laryngotracheal intubation, potentially resulting in complications such ventilator-associated pneumonia \u003csup\u003e\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e\u003c/sup\u003e. Therefore, for severe pneumonia patients on prolonged ventilator support with stable conditions, tracheotomy may be considered if extended ventilatory assistance is essential. Our study found that tracheotomy serves as a preventive factor against mortality associated with severe pneumonia, significantly reducing the risk of death. Nonetheless, owing to limitations in clinical data collection, the precise best present moment for incision requires additional investigation.\u003c/p\u003e \u003cp\u003ePneumonia is the major cause of septic shock, responsible for 50% of cases \u003csup\u003e\u003cspan additionalcitationids=\"CR40 CR41\" citationid=\"CR39\" class=\"CitationRef\"\u003e39\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e\u003c/sup\u003e. A retrospective clinical survey of 710 patients indicated that the mortality for individuals with severe pneumonia complicated with septic shock was greater than for those without septic shock \u003csup\u003e\u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e\u003c/sup\u003e. Our study identified concurrent septic shock as a significant risk factor for increased mortality in patients with severe pneumonia, corroborating findings from prior research \u003csup\u003e\u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e\u003c/sup\u003e and mutually confirming that septic shock is one of the two primary diagnostic criteria for severe pneumonia \u003csup\u003e\u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e43\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eTCM syndromes serve as significant indicators for disease progression, aiding in the prognostic assessment of patients according to their syndrome classifications or developments \u003csup\u003e\u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e\u003c/sup\u003e. Previous studies have shown that common symptoms of severe pneumonia include phlegm-heat obstructing lung syndrome, deficiency of both qi and yin syndrome, pathogenic qi falling into and prostration syndrome, and phlegm turbidity obstructing lung syndrome \u003csup\u003e\u003cspan citationid=\"CR45\" class=\"CitationRef\"\u003e45\u003c/span\u003e\u003c/sup\u003e. Our study identified that the pathogenic qi falling into and prostration syndrome were risk factors for mortality in severe pneumonia, with the presence of this syndrome frequently indicating a fatal outcome.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec19\" class=\"Section2\"\u003e \u003ch2\u003eStrengths compared to previous constructed models\u003c/h2\u003e \u003cp\u003eCurrently, multiple predictive models exist concerning the mortality risk associated with severe pneumonia. We did a thorough search and systematic comparison, revealing that the model we developed possesses particular characteristics and advantages. A study established the LR, gradient-boosted decision tree (LightGBM), and multilayer perceptron (MLP) models to forecast ICU mortality in patients with severe pneumonia \u003csup\u003e\u003cspan citationid=\"CR48\" class=\"CitationRef\"\u003e48\u003c/span\u003e\u003c/sup\u003e. The best MLP model achieved an AUC of 0.838, which was inferior than the AUC of 0.853 obtained by our XGBoost model. Both studies constructed multivariable LR models with an AUC of 0.836 \u003csup\u003e46\u003c/sup\u003e and 0.728 \u003csup\u003e47\u003c/sup\u003e for predicting in-hospital mortality in elderly patients with severe community-acquired pneumonia (SCAP). Additionally, another LR model, which lacked validation, reported an AUC as high as 0.915 in the training set \u003csup\u003e\u003cspan citationid=\"CR47\" class=\"CitationRef\"\u003e47\u003c/span\u003e\u003c/sup\u003e. A study \u003csup\u003e\u003cspan citationid=\"CR48\" class=\"CitationRef\"\u003e48\u003c/span\u003e\u003c/sup\u003e exclusively employed the LR method rather than machine learning algorithms to develop an in-hospital mortality risk prediction model for patients with SCAP. An alternative LR model predicting 30-day mortality in ICU patients with SCAP exhibited a lower AUC of 0.756 \u003csup\u003e49\u003c/sup\u003e. Nevertheless, our research additionally produced four models: SVM, DT, RF, and XGBoost, with the performance of our best model superior than that of models developed in prior studies.\u003c/p\u003e \u003cp\u003eIn summary, the model we developed possesses the following advantages: First of all, we employed multiple algorithms for machine learning, including SVM, DT, RF, and XGBoost, rather than solely relying on LR, and identified the optimal XGBoost model. Secondly, the optimal model we have developed exhibits markedly superior discrimination compared to previously published models, with an AUC of 0.853. Thirdly, and most importantly, prior models failed to incorporate TCM features, whereas our study first gathered 115 clinical features. Among the seven risk factors linked to in-hospital mortality in severe pneumonia identified by LASSO regression, two were TCM factors: TCM syndrome (pathogenic qi dropping into and prostration syndrome) and oral Chinese herbal decoction. Consequently, our model could provide a more comprehensive review of the severe pneumonia patients state and yield reliable predictions.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec20\" class=\"Section2\"\u003e \u003ch2\u003eLimitations\u003c/h2\u003e \u003cp\u003eOur study also has certain limitations. Initially, the absence of partial clinical data can lead to certain biases in the final outcomes. Our study depended on a retrospective research database. To ensure the reliability and accuracy of the research conclusions, our team cautiously managed quality control during data collection to acquire patient clinical data comprehensively and objectively. Despite employing different approaches to modeling and prospective validation, it remains impossible to eliminate issues such as missing clinical data records from the source, potentially resulting in biases in the final outcomes. Secondly, the sample size is rather limited. Clinical data for our investigation were acquired from two large hospitals. Despite the screening period starting in January 2008, the final sample size remained relatively small comparing to other diseases due to restricted medical conditions. A larger sample size in predictive model development provides more accurate findings. Consequently, we look forward to undertaking large-scale studies in multiple regions and institutions nationwide. Thirdly, not all machine learning algorithms are applied in this study. Our study selected five frequently employed algorithms and performed comparisons, but there are many machine learning algorithms that exist, and other algorithms such as Naive Bayes, Artificial Neural Networks, K-NN, etc. not used. Thus, we expect to investigate other machine learning techniques in the future to thoroughly assess and develop a more effective integrated risk model for severe pneumonia mortality, combining traditional Chinese and conventional treatment.\u003c/p\u003e \u003c/div\u003e"},{"header":"Conclusions","content":"\u003cp\u003eOlder age, increased BNU level, complication of septic shock, tracheotomy application, retention catheterization application, oral Chinese herbal decoction, and TCM syndrome (pathogenic qi falling into and prostration syndrome) may be potential risk factors that affect mortality in severe pneumonia, among which tracheotomy application and oral Chinese herbal decoction are protective factors. The XGBoost model exhibits superior overall performance in predicting hospital mortality risk for severe pneumonia, greater than traditional scoring systems such as PSI, SOFA, and APACHE II, which assists clinicians in prognostic assessment, resulting in improved therapeutic strategies and optimal resource allocation for patients.\u003c/p\u003e "},{"header":"Abbreviations","content":"\u003cp\u003eICU, intensive care unit; CRP, C-reactive protein; IL, interleukin; mNUTRIC, Modified Nutrition Risk in Critically ill; TCM, traditional Chinese medicine; AI, artificial intelligence; SOFA, Sequential Organ Failure Assessment; APACHE II, Acute Physiology and Chronic Health Evaluation II; LR, Logistic Regression; SVM, Support Vector Machine; DT, Decision Tree; RF, Random Forest; XGBoost, Extreme Gradient Boosting; H1N1, Influenza A; SARS, severe acute respiratory syndrome; COVID-19, coronavirus disease 2019;\u0026nbsp;COPD, chronic obstructive pulmonary disease;\u0026nbsp;WBC, white blood cell; RBC, red blood cell; NEUT%, neutrophilic granulocyte percentage; LY%, lymphocyte percentage; PCT, procalcitonin; AST, aminotransferase; ALT, alanine aminotransferase; BUN, blood urea nitrogen; Scr, serum creatinine; PT, prothrombin time; BNP, brain natriuretic peptide; PaO\u003csub\u003e2\u003c/sub\u003e,arterial partial pressure of oxygen; PaCO\u003csub\u003e2\u003c/sub\u003e, arterial partial pressure of carbon dioxide; PaO\u003csub\u003e2\u003c/sub\u003e/FiO\u003csub\u003e2\u003c/sub\u003e, arterial oxygenation index; SD, standard deviation; IQR, interquartile range; LASSO, Least Absolute Shrinkage and Selection Operator; AUROC, area under the receiver operating characteristic; ROC, receiver operation characteristic; AUC, area under the curve; DCA, decision curve analysis; PSI, Pneumonia Severity Index; SHAP, SHapley Additive exPlanations; LightGBM, gradient-boosted decision tree; MLP, multilayer perceptron; SCAP, severe community acquired pneumonia.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cdiv id=\"Sec22\" class=\"Section2\"\u003e \u003ch2\u003eData Availability Statement\u003c/h2\u003e \u003cp\u003eDue to confidentiality, data collected for the study are not publicly available for download. For further inquiries, please contact the corresponding author.\u003c/p\u003e \u003c/div\u003e\u003cp\u003e\u003cstrong\u003eAcknowledgements\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study was supported by the National Natural Science Foundation of China (No. 81774222, 82074411), Special Research Project of Traditional Chinese Medicine in Henan Province (No. 2023ZY1005), Construction project of traditional Chinese medicine in Henan Province (No. STG-ZYX02-202204), Henan University of Traditional Chinese Medicine\u0026rsquo;s Top Level Creation of Engineering Respiratory Disease Prevention and Treatment Technology Innovation Team in Traditional Chinese Medicine (No. HSRP-DFCTCM-T-1), Henan Province Traditional Chinese Medicine Top Level to Creation of a special scientific research topic (No. HSRP-DFCTCM-2023-3-21, HSRP-DFCTCM-2023-8-06).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthor contributions\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eKai Xie wrote the original draft, analysed and interpreted the data. Xiajin Huang, Zhen Li, Wenjing Yin, Xiaoxuan He, Xinyu Miao were responsible for the participants recruitment, information record, and data extraction. Haifeng Wang contributed to the study design and revised the manuscript. All authors read and approved the publication of this study.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting interests\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors declare that there is no conflict of interest regarding the publication of this paper.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthical approval\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study was approved by the Ethics Committee of the First Affiliated Hospital of Henan University of Chinese Medicine (No. 2023HL-241-01).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for Publication\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAll participants provided consent for the publication of findings.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAdditional information\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eCorrespondence and requests for materials should be addressed to Haifeng Wang.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eAbbas, K., Aboyans, M., Ackerman, I. \u0026amp; V., \u0026amp; Global burden of 369 diseases and injuries in 204 countries and territories, 1990\u0026ndash;2019: a systematic analysis for the global burden of disease study 2019. \u003cem\u003eLancet\u003c/em\u003e \u003cb\u003e396\u003c/b\u003e, 1204\u0026ndash;1222 (2020).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWelte, T., Torres, A. \u0026amp; Nathwani, D. Clinical and economic burden of community-acquired pneumonia among adults in Europe. \u003cem\u003eThorax\u003c/em\u003e \u003cb\u003e67\u003c/b\u003e, 71\u0026ndash;79 (2012).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAliberti, S. et al. Global initiative for meticillin-resistant staphylococcus aureus pneumonia (GLIMP): an international, observational cohort study. \u003cem\u003eLancet. Infect. Dis\u003c/em\u003e. \u003cb\u003e16\u003c/b\u003e, 1364\u0026ndash;1376 (2016).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMartin-Loeches, I., Garduno, A., Povoa, P. \u0026amp; Nseir, S. Choosing antibiotic therapy for severe community-acquired pneumonia. \u003cem\u003eCurr. Opin. Infect. Dis.\u003c/em\u003e \u003cb\u003e35\u003c/b\u003e, 133\u0026ndash;139 (2022).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen, J. et al. High mean platelet volume associates with in-hospital mortality in severe pneumonia patients. \u003cem\u003eMediat. Inflamm.\u003c/em\u003e (2020). (2020).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHuang, D. et al. Association of admission lactate with mortality in adult patients with severe community-acquired pneumonia. \u003cem\u003eAm. J. Emerg. Med.\u003c/em\u003e \u003cb\u003e65\u003c/b\u003e, 87\u0026ndash;94 (2023).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhang, C., Zheng, F. \u0026amp; Wu, X. Predictive value of C-Reactive protein-to-albumin ratio for risk of 28-day mortality in patients with severe pneumonia. \u003cem\u003eJ. Lab. Med.\u003c/em\u003e \u003cb\u003e47\u003c/b\u003e, 115\u0026ndash;120 (2023).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eEspana, P. P. et al. Development and validation of a clinical prediction rule for severe community-acquired pneumonia. \u003cem\u003eAm. J. Respir Crit. Care Med.\u003c/em\u003e \u003cb\u003e174\u003c/b\u003e, 1249\u0026ndash;1256 (2006).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAcehan, S. et al. MNUTRIC tool is capable to predict nutritional needs and mortality early in patients suffering from severe pneumonia. \u003cem\u003eClin. Nutr. ESPEN\u003c/em\u003e. \u003cb\u003e45\u003c/b\u003e, 184\u0026ndash;191 (2021).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMiao, L., Shen, X., Du, Z. \u0026amp; Liao, J. Stress hyperglycemia ratio and its influence on mortality in elderly patients with severe community-acquired pneumonia: a retrospective study. \u003cem\u003eAging Clin. Exp. Res.\u003c/em\u003e \u003cb\u003e36\u003c/b\u003e, 175 (2024).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLu, R. et al. Serum krebs von den lungen-6 is associated with in-hospital mortality of patients with severe community-acquired pneumonia: a retrospective cohort study. \u003cem\u003eClin. Chim. Acta\u003c/em\u003e. \u003cb\u003e548\u003c/b\u003e, 117524 (2023).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTseng, C. C. et al. The importance of high total body water/fat free mass ratio and serial changes in body composition for predicting hospital mortality in patients with severe pneumonia: a prospective cohort study. \u003cem\u003eBMC Pulm Med.\u003c/em\u003e \u003cb\u003e24\u003c/b\u003e, 470 (2024).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDos Santos Medeiros, S. M. D. F. et al. Predictive biomarkers of mortality in patients with severe COVID-19 hospitalized in intensive care unit. \u003cem\u003eFront. Immunol.\u003c/em\u003e \u003cb\u003e15\u003c/b\u003e, 1416715 (2024).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLee, J. et al. Severe thinness is associated with mortality in patients with community-acquired pneumonia: a prospective observational study. \u003cem\u003eAm. J. Emerg. Med.\u003c/em\u003e \u003cb\u003e33\u003c/b\u003e, 209\u0026ndash;213 (2015).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eQue, Y. A. et al. Low C-reactive protein values at admission predict mortality in patients with severe community-acquired pneumonia caused by streptococcus pneumoniae that require intensive care management. \u003cem\u003eInfection\u003c/em\u003e \u003cb\u003e43\u003c/b\u003e, 193\u0026ndash;199 (2015).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eXie, K. et al. Predictors of mortality in severe pneumonia patients: a systematic review and meta-analysis. \u003cem\u003eSyst. Rev.\u003c/em\u003e \u003cb\u003e13\u003c/b\u003e, 210 (2024).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRanstam, J., Cook, J. A. \u0026amp; Collins, G. S. Clinical prediction models. \u003cem\u003eBr. J. Surg.\u003c/em\u003e \u003cb\u003e103\u003c/b\u003e, 1886 (2016).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLi, J. et al. Machine learning prediction model for acute renal failure after acute aortic syndrome surgery. \u003cem\u003eFront. Med.\u003c/em\u003e \u003cb\u003e8\u003c/b\u003e, 728521 (2021).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBi, Q., Goodman, K. E., Kaminsky, J. \u0026amp; Lessler, J. What is machine learning? a primer for the epidemiologist. \u003cem\u003eAm. J. Epidemiol.\u003c/em\u003e \u003cb\u003e188\u003c/b\u003e, 2222\u0026ndash;2239 (2019).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePirracchio, R. et al. Mortality prediction in intensive care units with the super icu learner algorithm (sicula): a population-based study. \u003cem\u003eLancet Resp. Med.\u003c/em\u003e \u003cb\u003e3\u003c/b\u003e, 42\u0026ndash;52 (2015).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChinese Medical Association of respiratory disease branch. Diagnosis and treatment guidelines for adult community acquired pneumonia in China (2016 Edition). \u003cem\u003eC J. T R D\u003c/em\u003e. \u003cb\u003e39\u003c/b\u003e, 253\u0026ndash;279 (2016).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMetlay, J. P. et al. Diagnosis and treatment of adults with community-acquired pneumonia. an official clinical practice guideline of the American thoracic society and infectious diseases society of America. \u003cem\u003eAm. J. Respir Crit. Care Med.\u003c/em\u003e \u003cb\u003e200\u003c/b\u003e, e45\u0026ndash;e67 (2019).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYu, X., Xie, Y. \u0026amp; Li, J. Guidelines for the diagnosis and treatment of community-acquired pneumonia (2018 Revision). \u003cem\u003eJ. T C M\u003c/em\u003e. \u003cb\u003e60\u003c/b\u003e, 350\u0026ndash;360 (2019).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLASSO, R. R. R., M. A feature selection technique in predictive modeling for machine learning. \u003cem\u003eIEEE International Conference on Advances in Computer Applications (ICACA)\u003c/em\u003e, 2016:18\u0026ndash;20. (2016).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVan Calster, B. et al. Reporting and interpreting decision curve analysis: a guide for investigators. \u003cem\u003eEur. Urol.\u003c/em\u003e \u003cb\u003e74\u003c/b\u003e, 796\u0026ndash;804 (2018).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKassaw, G. et al. Outcomes and predictors of severe community-acquired pneumonia among adults admitted to the university of gondar comprehensive specialized hospital: a prospective follow-up study. \u003cem\u003eInfect. Drug Resist.\u003c/em\u003e \u003cb\u003e16\u003c/b\u003e, 619\u0026ndash;635 (2023).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDomaratzki, M. \u0026amp; Kidane, B. Deus Ex Machina? demystifying rather than deifying machine learning. \u003cem\u003eJ. Thorac. Cardiovasc. Surg.\u003c/em\u003e \u003cb\u003e163\u003c/b\u003e, 1131\u0026ndash;1137 (2022).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhu, W. et al. Delirium in hospitalized COVID-19 patients: a prospective, multicenter, cohort study. \u003cem\u003eJ. Neurol.\u003c/em\u003e \u003cb\u003e270\u003c/b\u003e, 4608\u0026ndash;4616 (2023).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eXie, K. et al. efficacy and safety of traditional chinese medicine adjuvant therapy for severe pneumonia: evidence mapping of the randomized controlled trials, systematic reviews, and meta-analyses. \u003cem\u003eFront. Pharmacol.\u003c/em\u003e \u003cb\u003e14\u003c/b\u003e, 1227436 (2023).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHepokoski, M. L., Bellinghausen, A. L., Bojanowski, C. M. \u0026amp; Malhotra, A. Can we DAMPen the cross-talk between the lung and kidney in the icU? \u003cem\u003eAm. J. Respir Crit. Care Med.\u003c/em\u003e \u003cb\u003e198\u003c/b\u003e, 1220\u0026ndash;1222 (2018).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWang, Z., Pu, Q., Huang, C. \u0026amp; Wu, M. Crosstalk between lung and extrapulmonary organs in infection and inflammation. \u003cem\u003eAdv. Exp. Med. Biol.\u003c/em\u003e \u003cb\u003e1303\u003c/b\u003e, 333\u0026ndash;350 (2021).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChawla, L. S. et al. Impact of acute kidney injury in patients hospitalized with pneumonia. \u003cem\u003eCrit. Care Med.\u003c/em\u003e \u003cb\u003e45\u003c/b\u003e, 600\u0026ndash;606 (2017).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDu, S. et al. Clinical factors associated with composition of lung microbiota and important taxa predicting clinical prognosis in patients with severe community-acquired pneumonia. \u003cem\u003eFront. Med.\u003c/em\u003e \u003cb\u003e16\u003c/b\u003e, 389\u0026ndash;402 (2022).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMahendra, M. et al. Factors influencing severity of community-acquired pneumonia. \u003cem\u003eLung India\u003c/em\u003e. \u003cb\u003e35\u003c/b\u003e, 284\u0026ndash;289 (2018).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eArvaniti, K. et al. Epidemiology and age-related mortality in critically Ill patients with intra-abdominal infection or sepsis: an international cohort study. \u003cem\u003eInt. J. Antimicrob. Agents\u003c/em\u003e. \u003cb\u003e60\u003c/b\u003e, 106591 (2022).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLi, Y., Wang, C. \u0026amp; Peng, M. Aging immune system and its correlation with liability to severe lung complications. \u003cem\u003eFront. Public. Health\u003c/em\u003e. \u003cb\u003e9\u003c/b\u003e, 735151 (2021).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWang, K. et al. Clinical and laboratory predictors of in-hospital mortality in patients with coronavirus disease-2019: a cohort study in wuhan, China. \u003cem\u003eClin. Infect. Dis.\u003c/em\u003e \u003cb\u003e71\u003c/b\u003e, 2079\u0026ndash;2088 (2020).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKaese, S., Zander, M. C. \u0026amp; Lebiedz, P. Successful use of early percutaneous dilatational tracheotomy and the no sedation concept in respiratory failure in critically ill obese subjects. \u003cem\u003eRespir Care\u003c/em\u003e. \u003cb\u003e61\u003c/b\u003e, 615\u0026ndash;620 (2016).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGuzzardella, A., Motos, A., Vallverdu, J. \u0026amp; Torres, A. Corticosteroids in sepsis and community-acquired pneumonia. \u003cem\u003eMed. Klin. Intensivmed Notfmed\u003c/em\u003e. \u003cb\u003e118\u003c/b\u003e, 86\u0026ndash;92 (2023).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSpencer, E., Rosengrave, P., Williman, J., Shaw, G. \u0026amp; Carr, A. C. Circulating protein carbonyls are specifically elevated in critically ill patients with pneumonia relative to other sources of sepsis. \u003cem\u003eFree Radic Biol. Med.\u003c/em\u003e \u003cb\u003e179\u003c/b\u003e, 208\u0026ndash;212 (2022).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eG\u0026uuml;ell, E. et al. Impact of lymphocyte and neutrophil counts on mortality risk in severe community-acquired pneumonia with or without septic shock. \u003cem\u003eJ. Clin. Med.\u003c/em\u003e \u003cb\u003e8\u003c/b\u003e, (2019).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eEspinoza, R. et al. Factors associated with mortality in severe community-acquired pneumonia: a multicenter cohort study. \u003cem\u003eJ. Crit. Care\u003c/em\u003e. \u003cb\u003e50\u003c/b\u003e, 82\u0026ndash;86 (2019).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFerrer, M. et al. Severe community-acquired pneumonia: characteristics and prognostic factors in ventilated and non-ventilated patients. \u003cem\u003ePLoS One\u003c/em\u003e \u003cb\u003e13\u003c/b\u003e, (2018).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLu, Y. \u0026amp; Deng, M. Inspiration from golden chamber synopsis for critically ill disease prognosis. \u003cem\u003eJ. T C M\u003c/em\u003e. \u003cb\u003e58\u003c/b\u003e, 661\u0026ndash;663 (2017).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhang, C., Guan, S., Xie, K., Zhang, K. \u0026amp; Wang, H. Distribution of clinical traditional Chinese medicine syndromes in patients with severe community-acquired pneumonia. \u003cem\u003eChin. Gen. Pract.\u003c/em\u003e \u003cb\u003e25\u003c/b\u003e, 2640\u0026ndash;2645 (2022).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eShang, N., Li, Q., Liu, H., Li, J. \u0026amp; Guo, S. Erector spinae muscle-based nomogram for predicting in-hospital mortality among older patients with severe community-acquired pneumonia. \u003cem\u003eBMC Pulm Med.\u003c/em\u003e \u003cb\u003e23\u003c/b\u003e, 346 (2023).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhu, Y. et al. Mortality Prediction using clinical and laboratory features in elderly patients with severe community-acquired pneumonia. \u003cem\u003eAnn. Palliat. Med.\u003c/em\u003e \u003cb\u003e10\u003c/b\u003e, 10913\u0026ndash;10921 (2021).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePan, J., Bu, W., Guo, T., Geng, Z. \u0026amp; Shao, M. Development and validation of an in-hospital mortality risk prediction model for patients with severe community-acquired pneumonia in the intensive care unit. \u003cem\u003eBMC Pulm Med.\u003c/em\u003e \u003cb\u003e23\u003c/b\u003e, 303 (2023).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhang, Y., Peng, Y., Zhang, W. \u0026amp; Deng, W. Development and validation of a predictive model for 30-day mortality in patients with severe community-acquired pneumonia in intensive care units. \u003cem\u003eFront. Med.\u003c/em\u003e \u003cb\u003e10\u003c/b\u003e, 1295423 (2023).\u003c/span\u003e\u003c/li\u003e\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":"Severe pneumonia, Machine learning, Prediction model, Mortality, Traditional Chinese medicine","lastPublishedDoi":"10.21203/rs.3.rs-5685118/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5685118/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eObjective: \u003c/strong\u003eWe aimed to develop an interpretable model to predict the mortality risk for patients with severe pneumonia.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMethods: \u003c/strong\u003eThe study retrospectively employed data from severe pneumonia patients hospitalized at the First Affiliated Hospital of Henan University of Chinese Medicine and Henan Provincial Hospital of Chinese Medicine between January 2008 and November 2021 as the training set for the model development. Patients with severe pneumonia admitted from the same two hospitals between December 2021 and January 2024 were prospectively included as the test set for the model evaluation. The demographic characteristics, clinical manifestations upon admission, risk factors upon admission, comorbidities, complications, laboratory results, treatment during hospitalization, other features, and fatal outcomes were collected. In the training set, all data were analyzed in comparison to survivors and non-survivors. The least absolute shrinkage and selection operator (LASSO) regression was applied to select features for the establishment of five models: logistic regression (LR), support vector machine (SVM), decision tree (DT), random forest (RF), and extreme gradient boosting (XGBoost). The performance of the models was assessed from discrimination, calibration and clinical practicability. The optimal model was screened out, and SHapley Additive exPlanation (SHAP) method was used to explain.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults:\u003c/strong\u003e A total of 323 eligible patients with severe pneumonia were enrolled, including 226 patients in the training set and 97 in the test set. In comparison to the other four models, the XGBoost model demonstrated the third highest AUROC (0.853), along with optimal calibration and clinical practicability. The SHAP value of the XGBoost model indicated that the retention catheterization applicationhad the strongest predictive value for all prediction horizons, closely followed by the variables of oral Chinese herbal decoction, BUN level, age, tracheotomy application, complication of septic shock, and TCM syndrome (pathogenic qi falling into and prostration syndrome).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusions:\u003c/strong\u003e Older age, increased BNU level, complication of septic shock, tracheotomy application, retention catheterization application, oral Chinese herbal decoction, and TCM syndrome (pathogenic qi falling into and prostration syndrome) may be potential risk factors that affect mortality in severe pneumonia, among which tracheotomy application and oral Chinese herbal decoction are protective factors. The XGBoost model exhibits superior overall performance in predicting hospital mortality risk for severe pneumonia, greater than traditional scoring systems such as PSI, SOFA, and APACHE II, which assists clinicians in prognostic assessment, resulting in improved therapeutic strategies and optimal resource allocation for patients.\u003c/p\u003e","manuscriptTitle":"Development and validation of a clinical prediction model for in-hospital mortality of severe pneumonia based on machine learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-07 12:43:30","doi":"10.21203/rs.3.rs-5685118/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":"359e17bd-521a-435f-b86f-3fd6139c58a3","owner":[],"postedDate":"April 7th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":46745695,"name":"Health sciences/Diseases/Respiratory tract diseases"},{"id":46745696,"name":"Health sciences/Diseases"},{"id":46745697,"name":"Health sciences/Risk factors"}],"tags":[],"updatedAt":"2025-07-03T06:53:39+00:00","versionOfRecord":[],"versionCreatedAt":"2025-04-07 12:43:30","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5685118","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5685118","identity":"rs-5685118","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}