Data from 4 medical centers were anonymized and integrated. Ethical approvals were granted by the respective ethics committees: Daping Hospital, Medical Research Ethics (2023) 261; Chongqing Emergency Medical Center, 2023 ethical review (48); the People’s Liberation Army Rocket Force Characteristic Medical Center (KY 2023037); and the General Hospital of Southern Theatre Command of People’s Liberation Army (NZLLKZ2024021). As this was a retrospective study, patient informed consent was waived by the ethics committees. It was registered with the Chinese Clinical Trial Registry (ChiCTR2300078097) and adhered to the Declaration of Helsinki. This study adheres to 2 key guidelines to ensure rigorous reporting: the TRIPOD-AI (Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis—Artificial Intelligence) guidelines for the development and reporting of multivariable ML predictive models in biomedical research (Multimedia Appendix 1) [16] and the STROCSS (Strengthening the Reporting of Cohort Studies in Surgery) criteria, which standardize the reporting of surgical observational studies [17].

The inclusion and exclusion criteria are as follows:

We retrieved patients who underwent trauma or concurrent surgeries using the MIMIC IV (Medical Information Mart for Intensive Care) 2.2 database, with the detailed data extraction process outlined in Multimedia Appendix 2. We then collected the necessary indicators using subject_id and hadm_id, which included the following information: ID number; sex; age; height; weight; type of surgery (elective or emergency); and preoperative comorbidities such as high blood pressure, diabetes, cerebrovascular diseases, chronic obstructive pulmonary disease, chronic bronchitis, asthma, and chronic renal insufficiency. Preoperative indicators included systolic blood pressure, heart rate (HR), saturation of pulse oximetry, and the presence of shock upon admission. The laboratory examination indicators (latest results prior to admission and first results postoperatively) included the following: complete blood count (white blood cell, lymphocyte [%], monocyte [%], neutrophil [%], eosinophil [%], basophil [%], RBC, mean corpuscular hemoglobin concentration, mean corpuscular volume, red cell distribution width, hemoglobin, hematocrit, platelet count [PLT], mean platelet volume, renal function [urea, creatinine, and blood uric acid]), liver function (albumin, alkaline phosphatase, lactate dehydrogenase, gamma-glutamyl transferase, total protein, globulin, direct bilirubin, indirect bilirubin, total bilirubin, alanine aminotransferase [ALT], and aspartate aminotransferase [AST]), electrolytes (sodium, potassium, and calcium), and coagulation function (activated partial thromboplastin time [APTT], prothrombin time [PT], international normalized ratio [INR], and D-dimer). The relevant intraoperative indicators included the need for perioperative blood transfusion. Complications during hospitalization included pulmonary embolism, sepsis, septicemia, heart failure, delirium, pulmonary edema, abnormal coagulation, endotracheal tube intubation, invasive mechanical ventilation, tracheostomy, end-stage renal disease, systemic inflammatory response, acute respiratory distress syndrome, pleural effusion, cardiac arrest, anemia, venous thrombosis, renal failure, acute kidney failure, urinary tract infection, respiratory failure, pneumonia, LOS, in-hospital death, and length of ICU stay. Data from the other 3 medical centers were collected via electronic medical records, consistent with the previously mentioned information. Our definition criteria for TIC were as follows: PLT<100×10^⁹/L; INR>1.25; PT>14 second; and APTT>36 second [18]. PPTIC was defined as patients who experienced TIC both within 24 hours before surgery (preoperative) and within 24 hours after surgery (postoperative), meeting one or more of the above TIC diagnostic criteria in both timeframes.

Statistical analysis was performed using SPSS Statistics (version 27.0; IBM Corp). Patients were divided into PPTIC and non-PPTIC groups, with PPTIC as the independent variable and other factors as dependent variables. Categorical data are presented as percentages, and continuous data as mean (SD). Depending on the distribution, continuous variables were assessed via 2-tailed t tests or Mann-Whitney U tests, and categorical variables via chi-square tests or exact tests. Univariate analysis identified risk factors for persistent trauma-induced coagulopathy, and multivariable logistic regression analyzed complications during hospitalization in the PPTIC group. A P value less than .05 was considered statistically significant.

We ultimately included 13,237 patients with trauma, among whom 6586 (49.8%) experienced PPTIC. The mean age of our patients was 62.45 (SD 17.85) years. In the PPTIC group, the average age was 63.6 (SD 17.4) years, whereas in the non-PPTIC group, it was 61.3 (SD 18.2) years, with P<.001 (Table 1). Among the patients, there were 5590 (42.2%) male individuals and 7646 (57.8%) female individuals, and this difference was significant (P<.001). The racial distribution included 3452 (26.1%) Asian individuals, 7402 (55.9%) White individuals, 342 (2.6%) Black individuals, 940 (7.1%) Latino individuals, and 1101(8.3%) individuals of other races.

Analysis of SHAP values highlighted the key features influencing model predictions. For RF, GB, and XGBoost (Figure 4), as well as the other 7 ML models (Multimedia Appendix 8), we observed the top 15 variables ranked by their average impact. In RF, the primary predictors of PPTIC in patients with trauma were preoperative APTT, PT, INR, AST, ALT, calcium, hemoglobin, sodium, hematocrit, admission SBP, RBC, admission HR, and the need for emergency surgery or perioperative blood transfusion (Table 3). Univariate logistic regression identified prolonged APTT, PT, and INR; low levels of hemoglobin, hematocrit, RBC, calcium, and sodium; elevated ALT and AST; and the need for emergency surgery or blood transfusion were significant risk factors for PPTIC.

Multivariate logistic regression analysis showed that compared with patients with non-PPTIC, those with PPTIC had significantly higher postoperative risks of the following complications: sepsis (1.75-fold, 95% CI 1.18-2.6; P=.006), heart failure (1.5-fold, 95% CI 1.24-1.82; P<.001), delirium (3.08-fold, 95% CI 1.62-5.83; P=.001), abnormal coagulation (3.57-fold, 95% CI 2.26-5.63; P<.001), tracheostomy (2.76-fold, 95% CI 2.02-3.77, P=.001), in-hospital mortality (2.19-fold, 95% CI 1.84-2.61; P<.001), urinary tract infection (1.95-fold, 95% CI 1.46-2.59; P<.001), and longer LOS and ICU stay (Figure 5).

Our study found that RF, GB, and XGBoost had AUROC values above 0.89 for predicting PPTIC, with RF performing best at 0.91. RF showed excellent performance across training, testing, and external validation sets. RF is an ML algorithm capable of capturing potential nonlinear relationships between risk factors and outcomes [22]. It operates by creating hundreds or thousands of smaller decision trees and combining their outputs for prediction [23]. This approach helps overcome the tendency of decision trees to overfit [23] while enhancing model generalizability [24]. Therefore, we recommend the use of the RF to predict the occurrence of PPTIC in patients with trauma. The prediction variables were primarily continuous laboratory indicators, eliminating the need for conversion into binary or categorical forms and facilitating practical use. Physicians can directly input these indicators into the RF model to assess the risk of PPTIC in patients with trauma. Recent guidelines highlight the importance of early detection and management of TIC to improve outcomes for severely injured patients [9]. Our study aims to predict PPTIC using preoperative indicators to facilitate early intervention and thereby improve clinical outcomes in such patients.

Most robust PPTIC prediction models in our study are tree-based, such as RF, DT, GB, and XGBoost, a trend also seen in other coagulopathy-related ML models. Perkins et al [25] used BN to predict early TIC, defined as an INR>1.2. Their model, trained on 600 patients with trauma, achieved an AUROC of 0.93 with a BS of 0.06 in the development dataset and an AUROC of 0.95 with a BS of 0.05 in the validation set [25]. In comparison, Our RF model achieved an AUROC of 1 in training, 0.92 in validation, and 0.91 in external validation, with BS values of 0.01, 0.10, and 0.13, respectively. Li et al [26] defined acute traumatic coagulopathy (ATC) as an INR>1.5 and collected data from 818 patients with trauma admitted to the emergency department. They used LR and RF to predict ATC occurrence, with LR achieving an AUROC of 0.858 and RF achieving an AUROC of 0.830 in the internal validation set [27]. Their study used only 2 ML models, with RF and LR achieving moderate predictive performance for ATC. Peltan et al [27] predicted the occurrence of prehospital ATC in 285 severely injured patients, defining coagulopathy as an INR>1.5, with an AUROC value of only 0.73. Previous studies had small sample sizes and moderate predictive power, and were limited to single centers without external validation. In contrast, our multicenter study employed 10 ML models, with 3 demonstrating excellent performance. It included diverse medical centers and populations (White, Asian, Black, and Latino) and featured external validation, showcasing the models’ broad applicability and generalizability.

The definition of TIC relies primarily on coagulation tests, drawing from extensive literature on the subject. Brohi et al [3] recommended that patients with a PT > 18 s, an INR > 1.5, an APTT>60 s, or a TT>15 s could be diagnosed with the hypocoagulable phenotype of TIC, and this diagnosis was not affected by the use of anticoagulant medications or abnormal blood samples. MacLeod et al [28] predicted early coagulopathy in 20,103 patients with trauma and reported a higher incidence after trauma, which was associated with mortality. They defined early coagulopathy as a PT>14 s, an APTT>35 s, and a PLT<100×10^9/L, highlighting its role as an independent predictor of death despite other risk factors [28]. Currently, the accepted definition of TIC utilizes the INR, with an INR>1.2 being the threshold for detecting TIC [8]. Yuan et al [18] defined TIC for predicting mortality among patients with trauma as a PLT<100×10⁹/L, an INR>1.25, a PT>14 seconds, and an APTT>36 seconds [18]. We defined TIC based on coagulation test reference ranges from various centers and literature, using slightly lower standards than Brohi et al [3]. The main reasons for adopting these criteria are as follows: (1) lower diagnostic criteria alert clinicians to take early preventive measures to prevent PPTIC from progressing to disseminated intravascular coagulation; and (2) patients with preexisting TIC have a 50% chance of persisting with TIC postoperatively.

The prolongation of the preoperative APTT, PT, and INR in patients with trauma is understandable as a risk factor for PPTIC. The decreases in hemoglobin, hematocrit, and RBC levels and lower admission DBP are associated mainly with acute anemia due to preoperative bleeding in patients with trauma. Ryan et al [29] noted a close correlation between initial low hematocrit or hemoglobin levels in patients with trauma and hemorrhagic shock. RBC and hematocrit levels are key factors in platelet transport and adhesion to endothelial injury. Platelet adhesion increases 5-fold when hematocrit rises from 10% to 40% [30]. Therefore, the RBC level is closely related to the platelet level. Steele et al [31] reported an independent correlation between hyponatremia at admission and hypocalcemia. Ionic calcium is crucial not only for the formation and stability of fibrin polymerization sites but also for many platelet-related functions [32]. Platelet activation and aggregation are also calcium-dependent [33] and play crucial roles in the pathophysiology of TIC [34]. Elevated ALT and AST levels indicate liver damage, which impacts coagulation factor production and the coagulation process.

Hess et al [35] reported that patients with TIC experience more blood loss, higher transfusion needs, and a greater incidence of MODS compared to those without TIC. Brohi et al [3] highlighted that TIC is associated with a 4-fold increase in mortality, increased rates of massive transfusion and MODS, and prolonged ICU and LOS. Smalls et al [36] reported that patients with TIC due to splenic injury face 2.4 times more complications, with increased mortality (1.3-fold), sepsis (2-fold), acute respiratory distress syndrome (2.6-fold), acute renal failure (1.5-fold), and cardiac arrest (1.5-fold). These findings align with our study, where patients with PPTIC had increased risks of sepsis (1.75-fold), heart failure (1.5-fold), delirium (3.08-fold), abnormal coagulation (3.57-fold), tracheostomy (2.76-fold), mortality (2.19-fold), urinary tract infection (1.95-fold), and longer LOS and ICU stay.

This retrospective study focused primarily on predicting PPTIC in patients with trauma via admission laboratory indicators and medical records. In this study, we addressed missing data to varying extents by excluding variables with more than 40% missing values and applying distinct imputation methods for variables with less than 40% missing data (KNN for continuous variables and multiple imputation for categorical variables). While multiple imputation is an effective method to mitigate systematic bias from nonrandom missing data, some data remained missing, which could affect the model’s predictive accuracy for specific patient characteristics. Due to missing values exceeding 40% for certain indicators, such as height, admission peripheral capillary oxygen saturation, temperature on admission, pre-lymphocyte, pre-total protein, pre-globulin, pre-direct bilirubin, pre-lactate dehydrogenase, pre-D-dimer, and post-D-dimer (Multimedia Appendix 3), these variables were excluded from model development. As these missing data may impact the predictive performance of the model, future studies could address this by collecting more comprehensive data to improve model robustness. Additionally, large-sample prospective clinical trials are necessary to validate the model’s applicability in clinical settings and assess its effectiveness in reducing the incidence of PPTIC.

Our study, using data from 4 medical centers, identified risk factors for PPTIC in patients with trauma. Significant factors included (1) prolonged preoperative APTT, PT, and INR; (2) decreased hemoglobin, hematocrit, RBC, calcium, and sodium levels; (3) lower admission DBP; (4) elevated ALT and AST levels; (5) increased admission HR; and (6) the need for emergency surgery or perioperative transfusion. PPTIC was associated with higher rates of sepsis, heart failure, delirium, abnormal coagulation, tracheostomy, mortality, and extended hospital and ICU stays. Of the 10 ML models evaluated for predicting PPTIC, RF demonstrated the best performance with an AUROC of 0.91, AUPRC of 0.89, accuracy of 0.84, and a BS of 0.13.