Chronic diseases spectrum and multimorbidity in elderly inpatients based on a 12-year epidemiological survey in China.

BACKGROUND: The number and proportion of the elderly population have been continuously increasing in China, leading to the elevated prevalence of chronic diseases and multimorbidity, which ultimately brings heavy burden to society and families. Meanwhile, the status of multimorbidity tends to be more complex in elderly inpatients than community population. In view of the above concerns, this study was designed to investigate the health status of elderly inpatients by analyzing clinical data in Chinese People's Liberation Army (PLA) General Hospital from 2008 to 2019, including the constitution of common diseases, comorbidities, the status of multimorbidity, in-hospital death and polypharmacy among elderly inpatients, so as to better understand the diseases spectrum and multimorbidity of elderly inpatients and also to provide supporting evidence for targeted management of chronic diseases in the elderly. METHODS: A clinical inpatients database was set up by collecting medical records of elderly inpatients from 2008 to 2019 in Chinese PLA General Hospital, focusing on diseases spectrum and characteristics of elderly inpatients. In this study, we collected data of inpatients aged ≥ 65 years old, and further analyzed the constitution of diseases, multimorbidity rates and mortality causes in the past decade. In addition, the prescriptions were also analyzed to investigate the status of polypharmacy in elderly inpatients. RESULTS: A total of 210,169 elderly patients were hospitalized from January 1st, 2008 to December 31st, 2019. The corresponding number of hospitalizations was 290,833. The average age of the study population was 72.67 years old. Of the total population, 73,493 elderly patients were re-admitted within one year, with the re-hospitalization rate of 25.27%. Malignant tumor, hypertension, ischemic heart disease, diabetes mellitus and cerebrovascular disease were the top 5 diseases. Among the study population, the number of patients with two or more long-term health conditions was 267,259, accounting for 91.89%, with an average of 4.68 diseases. In addition, the average number of medications taken by the study population was 5.4, among which, the proportion of patients taking more than 5 types of medications accounted for 55.42%. CONCLUSIONS: By analyzing the constitution of diseases and multimorbidity, we found that multimorbidity has turned out to be a prominent problem in elderly inpatients, greatly affecting the process of healthy aging and increasing the burden on families and society. Therefore, multidisciplinary treatment should be strengthened to make reasonable preventive and therapeutic strategies to improve the life quality of the elderly. Meanwhile, more attention should be paid to reasonable medications for elderly patients with multimorbidity to avoid preventable side effects caused by irrational medication therapy.

The Associations of Two Novel Inflammation Biomarkers, SIRI and SII, with Mortality Risk in Patients with Chronic Heart Failure.

Background: The associations of two novel inflammation biomarkers, systemic inflammation response index (SIRI) and systemic immune inflammation index (SII), with mortality risk in patients with chronic heart failure (CHF) are not well-characterized. Methods: This retrospective cohort study included patients with CHF in two medical centers of Chinese People's Liberation Army General Hospital, Beijing, China. The outcomes of this study included in-hospital mortality and long-term mortality. Associations of SIRI and SII with mortality were assessed using multivariable regressions and receiver operating characteristic (ROC) analyses. Results: A total of 6232 patients with CHF were included in the present study. We documented 97 cases of in-hospital mortality and 1738 cases of long-term mortality during an average 5.01-year follow-up. Compared with patients in the lowest quartile of SIRI, those in the highest quartile exhibited 134% higher risk of in-hospital mortality (adjusted odds ratio, 2.34; 95% confidence interval [CI], 1.16-4.72) and 45% higher risk of long-term mortality (adjusted hazard ratio, 1.45; 95% CI, 1.25-1.67). Compared with patients in the lowest quartile of SII, those in the highest quartile exhibited 27% higher risk of long-term mortality (adjusted hazard ratio, 1.27; 95% CI, 1.11-1.46). In ROC analyses, SIRI showed better prognostic discrimination than C-reactive protein (area under the curve: 69.39 vs 60.91, P = 0.01, for in-hospital mortality; 61.82 vs 58.67, P = 0.03, for 3-year mortality), whereas SII showed similar prognostic value with C-reactive protein. Conclusion: SIRI and SII were significantly associated with mortality risk in patients with CHF. SIRI may provide better prognostic discrimination than C-reactive protein.

Effect of early hemostasis strategy on secondary post-traumatic sepsis in trauma hemorrhagic patients.

INTRODUCTION: Fibrinogen and platelet, as the two main components of hemostatic resuscitation, are frequently administered in traumatic massive hemorrhage patients. It is reasonable to infer that they may have an impact on post-traumatic sepsis as more and more recognition of their roles in inflammation and immunity. This study aims to determine the association between the fibrinogen/platelet transfusion ratio during the first 24 h after trauma and the risk of the post- traumatic sepsis. METHODS: We analyzed the data from the National Trauma Data Bank (NTDB). Subjects included the critically injured adult patients admitted to Level I/II trauma center from 2013 to 2017 who received fibrinogen and platelet supplementation and more than 10 units (about 4000 ml) packed red blood cells (pRBCs) during the first 24 h after trauma. Two parts of analyses were performed: (1) multivariable stepwise regression was used to determine the variables that influence the risk of post-traumatic sepsis; (2) propensity score matching (PSM), to compare the influences of different transfusion ratio between fibrinogen and platelet on the risk of sepsis and other outcomes after trauma. RESULTS: 8 features were screened out by bi-directional multivariable stepwise logistic regression to predict the post-traumatic sepsis. They are age, sex, BMI, ISSabdomen, current smoker, COPD, Fib4h/24h and Fib/PLT24h. Fib/PLT24h was negatively related to sepsis (p < 0.05). A total of 1601 patients were included in the PSM cohort and grouped by Fib/PLT24h = 0.025 according to the fitting generalized additive model (GAM) model curve. The incidence of sepsis was significantly decreased in the high Fib/PLT group [3.3 % vs 9.4 %, OR = 0.33, 95 %CI (0.17-0.60)]; the length of stay in ICU and mechanical ventilation were both shortened as well [8 (IQR 2.00,17.00) vs 9 (IQR 3.00,19.25), p = 0.006 and 4 (IQR 2.00,10.00) vs 5 (IQR 2.00,14.00), p = 0.003, respectively. CONCLUSIONS: Early and sufficient supplementation of fibrinogen was a convenient way contribute to reduce the risk of sepsis after trauma.

Association between the triglyceride-glucose index and the risk of mortality among patients with chronic heart failure: results from a retrospective cohort study in China.

BACKGROUND: The triglyceride-glucose (TyG) index has been demonstrated to be a reliable surrogate marker of insulin resistance (IR) and an effective predictive index of cardiovascular (CV) disease risk. However, its long-term prognostic value in patients with chronic heart failure (CHF) remains uncertain. METHODS: A total of 6697 consecutive patients with CHF were enrolled in this study. Patients were divided into tertiles according to their TyG index. The incidence of primary outcomes, including all-cause death and CV death, was recorded. The TyG index was calculated as ln [fasting triglycerides (mg/dL) × fasting blood glucose (mg/dL)/2]. RESULTS: During a median follow-up of 3.9 years, a total of 2158 (32.2%) all-cause deaths and 1305 (19.5%) CV deaths were documented. The incidence of primary events from the lowest to the highest TyG index tertiles were 50.61, 64.64, and 92.25 per 1000 person-years for all-cause death and 29.05, 39.40, and 57.21 per 1000 person-years for CV death. The multivariate Cox hazards regression analysis revealed hazard ratios for all-cause and CV deaths of 1.84 (95% CI 1.61-2.10; P for trend < 0.001) and 1.94 (95% CI 1.63-2.30; P for trend < 0.001) when the highest and lowest TyG index tertiles were compared. In addition, the predictive ability of the TyG index against all-cause death was more prominent among patients with metabolic syndrome and those with heart failure with preserved ejection fraction phenotype (both P for interaction < 0.05). Furthermore, adding the TyG index to the established model for all-cause death improved the C­statistic value (0.710 for the established model vs. 0.723 for the established model + TyG index, P < 0.01), the integrated discrimination improvement value (0.011, P < 0.01), the net reclassification improvement value (0.273, P < 0.01), and the clinical net benefit (probability range, 0.07-0.36). CONCLUSIONS: The TyG index was significantly associated with the risk of mortality, suggesting that it may be a reliable and valuable predictor for risk stratification and an effective prognostic indicator in patients with CHF.

Application of Machine Learning Algorithms to Predict New-Onset Postoperative Atrial Fibrillation and Identify Risk Factors Following Isolated Valve Surgery.

BACKGROUND: New-onset postoperative atrial fibrillation (POAF) is the most common complication after valvular surgery, but its etiology and risk factors are incompletely understood. This study investigates the benefits of machine learning methods in risk prediction and in identifying relative perioperative variables for POAF after valve surgery. METHODS: This retrospective study involved 847 patients, who underwent isolated valve surgery from January 2018 to September 2021 in our institution. We used machine learning algorithms to predict new-onset postoperative atrial fibrillation and to select relatively important variables from a set of 123 preoperative characteristics and intraoperative information. RESULTS: The support vector machine (SVM) model demonstrated the best area under the receiver operating characteristic (AUC) value of 0.786, followed by logistic regression (AUC = 0.745) and the Complement Naive Bayes (CNB) model (AUC = 0.672). Left atrium diameter, age, estimated glomerular filtration rate (eGFR), duration of cardiopulmonary bypass, New York Heart Association (NYHA) class III-IV, and preoperative hemoglobin were high-ranked variables. CONCLUSIONS: Risk models based on machine learning algorithms may be superior to traditional models, which were primarily based on logistic algorithms to predict the occurrence of POAF after valve surgery. Further prospective multicenter studies are needed to confirm the performance of SVM in predicting POAF.

Joint association of hyperuricemia and chronic kidney disease with mortality in patients with chronic heart failure.

Background: The joint association of hyperuricemia and chronic kidney disease (CKD) with mortality in patients with chronic heart failure (CHF) is not conclusive. Methods: This retrospective cohort study was conducted in Chinese People's Liberation Army General Hospital, Beijing, China. We included 9,367 patients with CHF, who were hospitalized between January 2011 and June 2019. The definitions of hyperuricemia and CKD were based on laboratory test, medication use, and medical record. We categorized patients with CHF into 4 groups according to the absence (-) or presence (+) of hyperuricemia and CKD. The primary outcomes included in-hospital mortality and long-term mortality. We used multivariate logistic regression and Cox proportional hazards regression to estimate the mortality risk according to the hyperuricemia/CKD groups. Results: We identified 275 cases of in-hospital mortality and 2,883 cases of long-term mortality in a mean follow-up of 4.81 years. After adjusting for potential confounders, we found that compared with the hyperuricemia-/CKD- group, the risks of in-hospital mortality were higher in the hyperuricemia+/CKD- group (odds ratio [OR], 95% confidence interval [CI]: 1.58 [1.01-2.46]), hyperuricemia-/CKD+ group (OR, 95% CI: 1.67 [1.10-2.55]), and hyperuricemia+/CKD+ group (OR, 95% CI: 2.12 [1.46-3.08]). Similar results were also found in long-term mortality analysis. Compared with the hyperuricemia-/CKD- group, the adjusted hazard ratios and 95% CI for long-term mortality were 1.25 (1.11-1.41) for hyperuricemia+/CKD- group, 1.37 (1.22-1.53) for hyperuricemia-/CKD+ group, and 1.59 (1.43-1.76) for hyperuricemia+/CKD+ group. The results remained robust in the sensitivity analysis. Conclusions: Hyperuricemia and CKD, both individually and cumulatively, are associated with increased mortality risk in patients with CHF. These results highlighted the importance of the combined control of hyperuricemia and CKD in the management of heart failure.

Prediction of new onset postoperative atrial fibrillation using a simple Nomogram.

BACKGROUND: New onset postoperative atrial fibrillation (POAF) is the most common complication of cardiac surgery, with an incidence ranging from 15 to 50%. This study aimed to develop a new nomogram to predict POAF using preoperative and intraoperative risk factors. METHODS: We retrospectively analyzed the data of 2108 consecutive adult patients (> 18 years old) who underwent cardiac surgery at our medical institution. The types of surgery included isolated coronary artery bypass grafting, valve surgery, combined valve and coronary artery bypass grafting (CABG), or aortic surgery. Logistic regression or machine learning methods were applied to predict POAF incidence from a subset of 123 parameters. We also developed a simple nomogram based on the strength of the results and compared its predictive ability with that of the CHA2DS2-VASc and POAF scores currently used in clinical practice. RESULTS: POAF was observed in 414 hospitalized patients. Logistic regression provided the highest area under the receiver operating characteristic curve (ROC) in the validation cohort. A simple bedside tool comprising three variables (age, left atrial diameter, and surgery type) was established, which had a discriminative ability with a ROC of 0.726 (95% CI 0.693-0.759) and 0.727 (95% CI 0.676-0.778) in derivation and validation subsets respectively. The calibration curve of the new model was relatively well-fit (p = 0.502). CONCLUSIONS: Logistic regression performed better than machine learning in predicting POAF. We developed a nomogram that may assist clinicians in identifying individuals who are prone to POAF.

Association of Helicobacter pylori infection with survival outcomes in advanced gastric cancer patients treated with immune checkpoint inhibitors.

BACKGROUND: Accumulating evidence has revealed that the gut microbiota influences the effectiveness of immune checkpoint inhibitors (ICIs) in cancer patients. As a part of the human microbiome, Helicobacter pylori (H. pylori) was reported to be associated with reduced effectiveness of anti-PD1 immunotherapy in patients with non-small-cell lung cancer (NSCLC). Gastric cancer is more closely related to H. pylori, so we conducted a retrospective analysis to verify whether the association of H. pylori and effectiveness is applicable to advanced gastric cancer (AGC) patients. MATERIAL AND METHODS: AGC patients who had evidence of H. pylori and received anti-PD-1 antibodies were enrolled in the study. The differences in the disease control rate (DCR), overall survival (OS) and progression-free survival (PFS) between the H. pylori-positive group and the negative group were compared. RESULTS: A total of 77 patients were included in this study; 34 patients were H. pylori positive, and the prevalence of H. pylori infection was 44.2%. Compared with the H. pylori-negative group, patients in the H. pylori-positive group had a higher risk of nonclinical response to anti-PD-1 antibody, with an OR of 2.91 (95% CI: 1.13-7.50). Patients in the H. pylori-negative group had a longer OS and PFS than those in the positive group, with an estimated median OS of 17.5 months vs. 6.2 months (HR = 2.85, 95% CI: 1.70-4.78; P = 0.021) and a median PFS of 8.4 months vs. 2.7 months (HR = 3.11, 95% CI: 1.96-5.07, P = 0.008). Multivariate analysis indicated that H. pylori infection was independently associated with PFS (HR = 1.90, 95% CI: 1.10-3.30; P = 0.022). CONCLUSION: Our study unveils for the first time that H. pylori infection is associated with the outcome of immunotherapy for AGC patients. Multicenter, large sample and prospective clinical studies are needed to verify the association.

Establishment of a diagnostic model of coronary heart disease in elderly patients with diabetes mellitus based on machine learning algorithms.

OBJECTIVE: To establish a prediction model of coronary heart disease (CHD) in elderly patients with diabetes mellitus (DM) based on machine learning (ML) algorithms. METHODS: Based on the Medical Big Data Research Centre of Chinese PLA General Hospital in Beijing, China, we identified a cohort of elderly inpatients (≥ 60 years), including 10,533 patients with DM complicated with CHD and 12,634 patients with DM without CHD, from January 2008 to December 2017. We collected demographic characteristics and clinical data. After selecting the important features, we established five ML models, including extreme gradient boosting (XGBoost), random forest (RF), decision tree (DT), adaptive boosting (Adaboost) and logistic regression (LR). We compared the receiver operating characteristic curves, area under the curve (AUC) and other relevant parameters of different models and determined the optimal classification model. The model was then applied to 7447 elderly patients with DM admitted from January 2018 to December 2019 to further validate the performance of the model. RESULTS: Fifteen features were selected and included in the ML model. The classification precision in the test set of the XGBoost, RF, DT, Adaboost and LR models was 0.778, 0.789, 0.753, 0.750 and 0.689, respectively; and the AUCs of the subjects were 0.851, 0.845, 0.823, 0.833 and 0.731, respectively. Applying the XGBoost model with optimal performance to a newly recruited dataset for validation, the diagnostic sensitivity, specificity, precision, and AUC were 0.792, 0.808, 0.748 and 0.880, respectively. CONCLUSIONS: The XGBoost model established in the present study had certain predictive value for elderly patients with DM complicated with CHD.

Lipoprotein(a) is associated with coronary atheroma progression: analysis from a serial coronary computed tomography angiography study.

BACKGROUND: Lipoprotein(a) [Lp(a)] has been closely related to coronary atherosclerosis and might affect perivascular inflammation due to its proinflammatory properties. However, there are limited data about Lp(a) and related perivascular inflammation on coronary atheroma progression. Therefore, this study aimed to investigate the associations between Lp(a) and the perivascular fat attenuation index (FAI) with coronary atheroma progression detected by coronary computed tomography angiography (CCTA). METHODS: Patients who underwent serial CCTA examinations without a history of revascularization and with available data for Lp(a) within one month before or after baseline and follow-up CCTA imaging scans were considered to be included. CCTA quantitative analyses were performed to obtain the total plaque volume (TPV) and the perivascular FAI. Coronary plaque progression (PP) was defined as a ≥ 10% increase in the change of the TPV at the patient level or the presence of new-onset coronary atheroma lesions. The associations between Lp(a) or the perivascular FAI with PP were examined by multivariate logistic regression. RESULTS: A total of 116 patients were ultimately enrolled in the present study with a mean CCTA interscan interval of 30.80 ± 13.50 months. Among the 116 patients (mean age: 53.49 ± 10.21 years, males: 83.6%), 32 patients presented PP during the follow-up interval. Lp(a) levels were significantly higher among PP patients than those among non-PP patients at both baseline [15.80 (9.09-33.60) mg/dLvs. 10.50 (4.75-19.71) mg/dL,P = 0.029] and follow-up [20.60 (10.45-34.55) mg/dLvs. 8.77 (5.00-18.78) mg/dL,P = 0.004]. However, there were no differences in the perivascular FAI between PP group and non-PP group at either baseline or follow-up. Multivariate logistic regression analysis showed that elevated baseline Lp(a) level (OR = 1.031, 95% CI: 1.005-1.058,P = 0.019) was an independent risk factor for PP after adjustment for other conventional variables. CONCLUSIONS: Lp(a) was independently associated with coronary atheroma progression beyond low-density lipoprotein cholesterol and other conventional risk factors. Further studies are warranted to identify the inflammation effect exhibited as the perivascular FAI on coronary atheroma progression.

[Cardiac functional alterations and its risk factors in elderly patients with obstructive sleep apnea syndrome free of cardiovascular disease].

OBJECTIVE: To evaluate the changes of cardiac structure and function and their risk factors in elderly patients with obstructive sleep apnea syndrome (OSA) without cardiovascular complications. METHODS: Eighty-two elderly OSA patients without cardiovascular disease admitted between January, 2015 and October, 2016 were enrolled in this study. According to their apnea-hypopnea index (AHI, calculated as the average number of episodes of apnoea and hypopnoea per hour of sleep), the patients were divided into mild OSA group (AHI < 15) and moderate to severe OSA group (AHI ≥ 15). The demographic data and the general clinical data were recorded and fasting blood samples were collected from the patients on the next morning following polysomnographic monitoring for blood cell analysis and biochemical examination. Echocardiography was performed within one week after overnight polysomnography, and the cardiac structure, cardiac function and biochemical indexes were compared between the two groups. RESULTS: Compared with those with mild OSA group, the patients with moderate to severe OSA had significantly higher hematocrit (0.22±0.08 vs 0.17±0.04, P=0.032) and serum creatinine level (70.94± 27.88 vs 54.49±34.22 µmol/L, P=0.022). The left ventricular ejection fraction, interventricular septal thickness, left ventricular posterior wall thickness, left atrial diameter and left ventricular end-diastolic diameter were all similar between the two groups. With a similar early diastolic mitral flow velocity (E) between the two groups, the patients with moderate to severe OSA had a significantly higher late diastolic mitral flow velocity (A) (70.35±6.87 vs 64.09±8.31, P=0.0001) and a significantly lower E/A ratio (0.98±0.06 vs 1.08±0.05, P=0.0001) than the patients with mild OSA. Multiple linear regression showed that the E/A ratio was negatively correlated with AHI (ß =- 0.645, P=0.0001). CONCLUSIONS: Cardiac diastolic function impairment may occur in elderly patients with moderate or severe OSA who do not have hypertension or other cardiovascular diseases, and the severity of the impairment is positively correlated with AHI.

[Correlation between severity of obstructive sleep apnea syndrome and red cell distribution width in elderly patients].

OBJECTIVE: To investigate the correlation between the severity of obstructive sleep apnea syndrome (OSAS) and red cell distribution width (RDW) in elderly patients. METHODS: A cross-sectional study was conducted among 311 elderly patients diagnosed with OSAS in the snoring clinic between January, 2015 and October, 2016 and 120 healthy controls without OSAS from physical examination populations in the General Hospital of PLA. The subjects were divided into control group with apnea-hypopnea index (AHI) <5 (n=120), mild OSAS group (AHI of 5.0-14.9; n=90), moderate OSAS group (AHI of 15.0-29.9; n=113) and severe OSAS group (AHI ≥ 30; n=108). The clinical characteristics and the results of polysomnography, routine blood tests and biochemical tests of the subjects were collected. Multiple linear regression analysis was used to examine the correlation between OSAS severity and RDW. RESULTS: The levels of RDW and triglyceride were significantly higher in severe OSAS group than in the other groups (P < 0.01). The levels of fasting blood glucose and body mass index were significantly higher in severe and moderate OSAS groups than in mild OSAS group and control group (P < 0.05 or P < 0.01). Multiple linear regression analysis showed that AHI was positively correlated with body mass index (ß=0.111, P=0.032) and RDW (ß=0.106, P=0.029). The area under ROC curve of RDW for predicting the severity of OSAS was 0.687 (P=0.0001). CONCLUSIONS: The RDW increases as OSAS worsens and may serve as a potential marker for evaluating the severity of OSAS.

Prediction of fatal adverse prognosis in patients with fever-related diseases based on machine learning: A retrospective study.

BACKGROUND: Fever is the most common chief complaint of emergency patients. Early identification of patients at an increasing risk of death may avert adverse outcomes. The aim of this study was to establish an early prediction model of fatal adverse prognosis of fever patients by extracting key indicators using big data technology. METHODS: A retrospective study of patients' data was conducted using the Emergency Rescue Database of Chinese People's Liberation Army General Hospital. Patients were divided into the fatal adverse prognosis group and the good prognosis group. The commonly used clinical indicators were compared. Recursive feature elimination (RFE) method was used to determine the optimal number of the included variables. In the training model, logistic regression, random forest, adaboost and bagging were selected. We also collected the emergency room data from December 2018 to December 2019 with the same inclusion and exclusion criterion. The performance of the model was evaluated by accuracy, F1-score, precision, sensitivity and the areas under receiver operator characteristic curves (ROC-AUC). RESULTS: The accuracy of logistic regression, decision tree, adaboost and bagging was 0.951, 0.928, 0.924, and 0.924, F1-scores were 0.938, 0.933, 0.930, and 0.930, the precision was 0.943, 0.938, 0.937, and 0.937, ROC-AUC were 0.808, 0.738, 0.736, and 0.885, respectively. ROC-AUC of ten-fold cross-validation in logistic and bagging models were 0.80 and 0.87, respectively. The top six coefficients and odds ratio (OR) values of the variables in the Logistic regression were cardiac troponin T (CTnT) (coefficient=0.346, OR = 1.413), temperature (T) (coefficient=0.235, OR = 1.265), respiratory rate (RR) (coefficient= -0.206,OR = 0.814), serum kalium (K) (coefficient=0.137, OR = 1.146), pulse oxygen saturation (SPO2) (coefficient= -0.101, OR = 0.904), and albumin (ALB) (coefficient= -0.043, OR = 0.958). The weights of the top six variables in the bagging model were: CTnT, RR, lactate dehydrogenase, serum amylase, heartrate, and systolic blood pressure. CONCLUSIONS: The main clinical indicators of concern included CTnT, RR, SPO2, T, ALB and K. The bagging model and logistic regression model had better diagnostic performance comprehesively. Those may be conducive to the early identification of critical patients with fever by physicians.

A Machine Learning-Based Model to Predict Acute Traumatic Coagulopathy in Trauma Patients Upon Emergency Hospitalization.

Acute traumatic coagulopathy (ATC) is an extremely common but silent murderer; this condition presents early after trauma and impacts approximately 30% of severely injured patients who are admitted to emergency departments (EDs). Given that conventional coagulation indicators usually require more than 1 hour after admission to yield results-a limitation that frequently prevents the ability for clinicians to make appropriate interventions during the optimal therapeutic window-it is clearly of vital importance to develop prediction models that can rapidly identify ATC; such models would also facilitate ancillary resource management and clinical decision support. Using the critical care Emergency Rescue Database and further collected data in ED, a total of 1385 patients were analyzed and cases with initial international normalized ratio (INR) values >1.5 upon admission to the ED met the defined diagnostic criteria for ATC; nontraumatic conditions with potentially disordered coagulation systems were excluded. A total of 818 individuals were collected from Emergency Rescue Database as derivation cohorts, then were split 7:3 into training and test data sets. A Pearson correlation matrix was used to initially identify likely key clinical features associated with ATC, and analysis of data distributions was undertaken prior to the selection of suitable modeling tools. Both machine learning (random forest) and traditional logistic regression were deployed for prediction modeling of ATC. After the model was built, another 587 patients were further collected in ED as validation cohorts. The ATC prediction models incorporated red blood cell count, Shock Index, base excess, lactate, diastolic blood pressure, and potential of hydrogen. Of 818 trauma patients filtered from the database, 747 (91.3%) patients did not present ATC (INR ≤ 1.5) and 71 (8.7%) patients had ATC (INR > 1.5) upon admission to the ED. Compared to the logistic regression model, the model based on the random forest algorithm showed better accuracy (94.0%, 95% confidence interval [CI]: 0.922-0.954 to 93.5%, 95% CI: 0.916-0.95), precision (93.3%, 95% CI: 0.914-0.948 to 93.1%, 95% CI: 0.912-0.946), F1 score (93.4%, 95% CI: 0.915-0.949 to 92%, 95% CI: 0.9-0.937), and recall score (94.0%, 95% CI: 0.922-0.954 to 93.5%, 95% CI: 0.916-0.95) but yielded lower area under the receiver operating characteristic curve (AU-ROC) (0.810, 95% CI: 0.673-0.918 to 0.849, 95% CI: 0.732-0.944) for predicting ATC in the trauma patients. The result is similar in the validation cohort. The values for classification accuracy, precision, F1 score, and recall score of random forest model were 0.916, 0.907, 0.901, and 0.917, while the AU-ROC was 0.830. The values for classification accuracy, precision, F1 score, and recall score of logistic regression model were 0.905, 0.887, 0.883, and 0.905, while the AU-ROC was 0.858. We developed and validated a prediction model based on objective and rapidly accessible clinical data that very confidently identify trauma patients at risk for ATC upon their arrival to the ED. Beyond highlighting the value of ED initial laboratory tests and vital signs when used in combination with data analysis and modeling, our study illustrates a practical method that should greatly facilitates both warning and guided target intervention for ATC.