Objective:To develop a grading prediction model of traumatic hemorrhage volume based on deep learning and assist in predicting traumatic hemorrhage volume.Methods:A retrospective observational study was conducted based on the experimental data of pig gunshot wounds in the time-effect assessment database for experiments on war-traumatized animals constructed by the General Hospital of the Chinese People's Liberation Army. The hemorrhage volume data of the study population were extracted, and the animals were divided into 0-300 mL, 301-600 mL, and > 600 mL groups according to the hemorrhage volume. Using vital signs indexes as the predictive variables and hemorrhage volume grading as the outcome variable, trauma hemorrhage volume grading prediction models were developed based on four traditional machine learning and ten deep learning methods. Using laboratory test indexes as predictive variables and hemorrhage volume grading as outcome variables, trauma hemorrhage volume grading prediction models were developed based on the above fourteen methods. The effect of the two groups of models was evaluated by accuracy and area under the receiver operator characteristic curve (AUC), and the optimal models in the two groups were mixed to obtain hybrid model 1. Feature selection was conducted according to the genetic algorithm, and hybrid model 2 was constructed according to the best feature combination. Finally, hybrid model 2 was deployed in the animal experiment database system.Results:Ninety-six traumatic animals in the database were enrolled, including 27 pigs in the 0-300 mL group, 40 in the 301-600 mL group, and 29 in the > 600 mL group. Among the fourteen models based on vital signs indexes, fully convolutional network (FCN) model was the best [accuracy: 60.0%, AUC and 95% confidence interval (95% CI) was 0.699 (0.671-0.727)]. Among the fourteen models based on laboratory test indexes, recurrent neural network (RNN) model was the best [accuracy: 68.9%, AUC (95% CI) was 0.845 (0.829-0.860)]. After mixing the FCN and RNN models, the hybrid model 1, namely RNN-FCN model was obtained, and the performance of the model was improved [accuracy: 74.2%, AUC (95% CI) was 0.847 (0.833-0.862)]. Feature selection was carried out by genetic algorithm, and the hybrid model 2, namely RNN-FCN* model, was constructed according to the selected feature combination, which further improved the model performance [accuracy: 80.5%, AUC (95% CI) was 0.880 (0.868-0.893)]. The hybrid model 2 contained ten indexes, including mean arterial pressure (MAP), hematocrit (HCT), platelet count (PLT), lactic acid, arterial partial pressure of carbon dioxide (PaCO 2), Total CO 2, blood sodium, anion gap (AG), fibrinogen (FIB), international normalized ratio (INR). Finally, the RNN-FCN* model was deployed in the database system, which realized automatic, continuous, efficient, intelligent, and grading prediction of hemorrhage volume in traumatic animals. Conclusion:Based on deep learning, a grading prediction model of traumatic hemorrhage volume was developed and deployed in the information system to realize the intelligent grading prediction of traumatic animal hemorrhage volume.

Objective:To establish a stable fragment-induced penetrating liver injury model in landrace pigs and evaluate the characteristics of deep tissue injury.Methods:According to the different positioning methods of aiming points, twelve healthy adult landrace pigs were divided into group A (the relative height "h" of the aiming point and the highest point of the body surface on the tracing line was set to 5 cm) and group B ("h" was set to 6 cm). Ultrasonography was used to determine the direction of fragment projection, and an experimental ballistic gun was used to project high-velocity fragments to cause injury to animals. The vital signs of the two groups were monitored, and whole blood cell count, blood gas analysis, and liver and renal function were tested. Damages to the liver and adjacent organs, as well as the amount of bleeding and survival time were analyzed.Results:For the overall analysis of the two groups, the liver hit rate of fragment simulating projectiles was 100% (right anterior lobe and right lateral lobe injury), the hit rate of other organs in the abdominal cavity was 25% (3/12), and the incidence of hemothorax or pneumothorax was 8% (1/12). The wounds were mainly characterized by liver lacerations, with total or partial disconnection of the distal liver lobe. There was no significant difference in wound length and bleeding amount between groups A and B [wound length (cm): 9.8±1.7 vs. 11.2±3.8, bleeding amount (g): 597.0±477.1 vs. 1 032.0±390.3, both P > 0.05]. The depth of liver parenchymal laceration in group B with the aiming point closer to the anterior median line was significantly longer than that in group A (cm: 2.8±0.4 vs. 1.9±0.6, P = 0.015). Mean arterial pressure (MAP), pH value, residual arterial blood base (BE), hemoglobin (Hb) and hematocrit (HCT) levels decreased after the fragment-induced injury, and then reached a trough level [MAP (mmHg, 1 mmHg ≈ 0.133 kPa): 87.0±33.6, pH: 7.26±0.15, BE (mmol/L): -6.65±8.48, Hb (g/L): 9.86±1.10, HCT: 0.309±0.029, all P < 0.05] in the first hour. Blood lactate (Lac), lactate dehydrogenase (LDH) and aspartate aminotransferase (AST) levels increased over time, and reached a peak level [Lac (mmol/L): 10.21±4.40, LDH (U/L): 1 417.0±223.3, AST (U/L): 234.5 (162.5, 357.5), both P < 0.05] at 1 hour after injury. Pearson's correlation analysis showed that the total amount of bleeding was correlated with the depth of liver parenchyma laceration ( r = 0.684, P = 0.014). The Kaplan-Meier survival curve showed that the 3 hours survival rate in group A was higher than that in group B, but the difference was not statistically significant [83.3% (5/6) vs. 33.3% (2/6), P > 0.05]. Conclusions:The high-velocity fragment-induced penetrating liver injury model established by striking landrace pigs closer to the anterior median line with fragment simulating projectiles is reproducible and the degree of damage is controllable, and the model is applicable to further relevant research of hepatic ballistic trauma.

Objective:To observe the changes of arterial blood gas indexes in pigs with the free-field primary blast lung injury (PBLI) model, and to explore the value of arterial blood gas indexes in predicting moderate to severe PBLI.Methods:Nine adult healthy Landrace pigs were selected to construct the pig free-field PBLI model. Arterial blood samples were taken 15 minutes before the explosion (before injury) and 10, 30, 60, 120, and 180 minutes after the explosion (after injury). Arterial blood gas indexes and pulse oxygen saturation (SpO 2) were measured, compare the changes of blood gas analysis indexes and SpO 2 levels at different time points, and observe the changes of gross injury scores and pathological injury scores of lung tissue. Analyze the correlation between the blood gas indicators. Results:As time prolonged, at each time point, pH, arterial partial pressure of oxygen (PaO 2), and SpO 2 were lower than those before the injury, and blood lactic acid (Lac) and arterial partial pressure of carbon dioxide (PaCO 2) were higher than those before the injury. Compared with that before the injury, the pH value in the blood decreased significantly 10 minutes after the injury (7.39±0.06 vs. 7.46±0.02, P < 0.05), and the Lac increased significantly (mmol/L: 3.61±2.89 vs. 1.10±0.28, P < 0.05), and lasts until 180 minutes after injury (pH value: 7.37±0.07 vs. 7.46±0.02, Lac (mmol/L): 2.40±0.79 vs. 1.10±0.28, both P < 0.05); while PaO 2 and SpO 2 decreased significantly at 180 minutes after injury [PaO 2 (mmHg, 1 mmHg = 0.133 kPa): 59.40±10.94 vs. 74.81±9.39, P < 0.05; SpO 2: 0.75±0.11 vs. 0.89±0.08, P < 0.05], PaCO 2 increased significantly (mmHg: 56.17±5.38 vs. 48.42±4.93, P < 0.05). Correlation analysis showed that the gross injury score of lung blast injury animals was positively correlated with the pathological injury score ( r = 0.866, P = 0.005); PaO 2 and SpO 2 were positively correlated ( r = 0.703, P = 0.000); pH value and Lac were negative Correlation ( r = -0.400, P = 0.006); pH value is negatively correlated with PaCO 2 ( r = -0.844, P = 0.000). Conclusion:This study successfully established a large mammalian free-field PBLI model, arterial blood gas analysis is helpful for the early diagnosis of PBLI, whether SpO 2 can be used to evaluate the severity of lung injury remains to be further verified.

Blast injury is the main cause of injury in the battlefield, which also occurs frequently in the civil field and modern society. The damage caused by blast is more complicated than other types of trauma. Primary blast injury is a common type of blast injury, which can cause multiple organ damage with complex mechanism. Tissue and vascular endothelium damage and organ hypoperfusion are the consistent manifestations of most organ damage. However, due to the concealed damage caused by the primary blast injury, it is difficult to recognize it in time. The study of coagulation function and acid-base balance change after primary blast injury can bring benefits to its early diagnosis and intervention, thus improving the prognosis and mortality of blast injury. However, at present, the research on primary blast injury mostly focuses on single organ damage. Lack of research on systemic coagulation and acid-base balance changes calls for further research. Such research has a practical significance for the early diagnosis and optimization of tactical care for primary blast injury. This article reviews the injury characteristics, epidemiology, mechanism and the relationship with trauma-induced coagulopathy (TIC) in primary blast injury to provide reference for related researches.

Medical big data is a hot research topic in China,and it is also the main research direction in the field of emergency medicine.The current situation of the construction of the first-aid big data platform and the construction of the first-aid clinical decision support system were analyzed,the problems existing in the development of the first-aid big data research field were enumerated,to explore the theoretical methods for promoting the development of domestic first-aid big data,so as to provide references for the research in related fields.

On?the?premise?of?fully?studying?the?disaster?medical?rescue?monitoring?mechanism?in?emergencies?at?home?and?abroad,?the?functional?requirements?of?the?domestic?disaster?medical?rescue?monitoring?system?was?analyzed?in?this?paper,?the?logical?framework?and?data?structure?of?disaster?medical?rescue?monitoring?system?with?privacy?protection?mechanism?was?designed?by?department?of?emergency?in?Chinese?PLA?General?Hospital,?department?of?information?management?in?School?of?Economics?and?Management?of?Beijing?Jiaotong?University,?the?School?of?Information?Management?of?Nanjing?University.?Three?major?functional?modules?were?realized?in?the?system:?reporter?information?management,?disaster?medical?rescue?data?upload,?and?disaster?medical?rescue?data?search.?Android?client?and?Web?client?were?developed?for?easy?access?to?the?system.?The?system?also?had?the?function?of?privacy?protection.?Based?on?symmetric?searchable?encryption?algorithm,?the?system?realized?the?encryption?storage?of?untrusted?servers?and?ensured?the?security?of?medical?and?health?data.?It?is?beneficial?for?the?further?development?and?improvement?of?disaster?medical?rescue?data?collection?in?China.

The analysis of big data in medical field cannot be isolated from the high quality clinical database, and the construction of first aid database in our country is still in the early stage of exploration. This paper introduces the idea and key technology of the construction of multi-parameter first aid database. By combining emergency business flow with information flow, an emergency data integration model was designed with reference to the architecture of the Medical Information Mart for Intensive Care III (MIMIC-III), created by Computational Physiology Laboratory of Massachusetts Institute of Technology (MIT), and a high-quality first-aid database was built. The database currently covers 22 941 medical records for 19 814 different patients from May 2015 to October 2017, including relatively complete information on physiology, biochemistry, treatment, examination, nursing, etc. And based on the database, the first First-Aid Big Data Datathon event, which 13 teams from all over the country participated in, was launched. The First-Aid database provides a reference for the construction and application of clinical database in China. And it could provide powerful data support for scientific research, clinical decision making and the improvement of medical quality, which will further promote secondary analysis of clinical data in our country.
Big Data ; Critical Care ; Databases, Factual ; Humans ; Medical Informatics

OBJECTIVE: To propose a method of prediction for fatal gastrointestinal bleeding recurrence in hospital and a method of feature selection via machine learning models. METHODS: 728 digestive tract hemorrhage samples were extracted from the first aid database of PLA General Hospital, and 343 patients among them were diagnosed as fatal gastrointestinal bleeding recurrence in hospital. A total of 64 physiological or laboratory indicators were extracted and screened. Based on the ten-fold cross-validation, Logistic regression, AdaBoost and XGBoost were used for classification prediction and comparison. XGBoost was used to search sequence features, and the key indicators for predicting fatal gastrointestinal bleeding recurrence in hospital were screened out according to the importance of the indicators during training. RESULTS: Logistic regression, AdaBoost and XGBoost all get better F1.5 score under each feature input dimension, among which XGBoost had the best effect and the highest score, which was able to identify as many patients as possible who might have fatal gastrointestinal bleeding recurrence in hospital. Through XGBoost iteration results, the Top 30 indicators with high importance for predicting fatal gastrointestinal bleeding recurrence in hospital were ranked. The F1.5 scores of the first 12 key indicators peaked at iteration (0.893), including hemoglobin (Hb), calcium (CA), red blood cell count (RBC), mean platelet volume (MPV), mean erythrocyte hemoglobin concentration (MCH), systolic blood pressure (SBP), platelet count (PLT), magnesium (MG), lymphocyte (LYM), glucose (GLU, blood gas analysis), glucose (GLU, blood biochemistry) and diastolic blood pressure (DBP). CONCLUSIONS Logistic regression, AdaBoost and XGBoost could achieve the purpose of early warning for predicting fatal gastrointestinal bleeding recurrence in hospital, and XGBoost is the most suitable. The 12 most important indicators were screened out by sequential forward selection.
Gastrointestinal Hemorrhage/mortality* ; Health Status Indicators ; Hospital Mortality ; Humans ; Logistic Models ; Machine Learning ; Recurrence

Objective To analyze the correlation between acute coronary syndrome (ACS) and stress differentiation factors (GDF-15), catecholamines, and heat shock proteins (HSP-70). Methods A total of 40 patients with ACS were selected from the Emergency Department of the PLA General Hospital from September 10, 2016 to October 10, 2016. 40 healthy volunteers were selected as the control group. The information of age, gender, history of smoking, drinking, hyperlipidemia, hypertension and diabetes. Inspection indicators of blood biochemistry (Creation kinase Isoenzyme, Total cholesterol, Triglyceride, High-density lipoprotein, Blood glucose, Total bilirubin, Direct bilirubin), serum level of GDF-15, catecholamine (Adrenaline,norepinephrine,dopamine)and HSP-70 were collected. Evaluation of Coronary Stenosis used with Coronary Artery Lesions and Gensini Score. Statistical analysis using SPSS 17.0 statistical software, measurement data are expressed as mean ± standard deviation (x±s),count data to the number of cases and percentage, measurement using t test, count data using chisquare test. Results Serum levels of GDF-15[(21.94±14.23) vs. (7.06±5.53), P=0.007],catecholami ne[(46592.15±30931.27) vs. (5507.14±2083.28), P<0.01], HSP-70 [(369.56±300.44) vs. (07.76±54.23),P<0.001],all higher than the control group. GDF-15 serum levels of Gensini scores> 40 compare with <20group was significantly higher [(324.27 ± 198.81) vs. (77.43 ± 699.22), P=0.035], serum catecholaminelevels of > 40 group compare with <20 group significantly increased [(18.71 ± 7.32) vs. (18.6±46.1),P=0.017], GDF-15 levels were significantly higher in the multi-vessel stenosis group than in the doublevessel stenosis group[ (618.40±434.42) vs. (292.07±219.65), P=0.033]. Conclusions GDF-15,catecholamine and HSP-70 are correlated with ACS, as well as the severity of coronary artery lesions.

To introduce Medical Information Mart for Intensive Care (MIMIC) database and elaborate the approach of critically emergent research with big data based on the feature of MIMIC and updated studies both domestic and overseas, we put forward the feasibility and necessity of introducing medical big data to research in emergency. Then we discuss the role of MIMIC database in emergency clinical study, as well as the principles and key notes of experimental design and implementation under the medical big data circumstance. The implementation of MIMIC database in emergency medical research provides a brand new field for the early diagnosis, risk warning and prognosis of critical illness, however there are also limitations. To meet the era of big data, emergency medical database which is in accordance with our national condition is needed, which will provide new energy to the development of emergency medicine.