Background: Recent research has revealed the potential value of machine learning (ML) models in improving prognostic prediction for patients with trauma. ML can enhance predictions and identify which factors contribute the most to posttraumatic mortality. However, no studies have explored the risk factors, complications, and risk prediction of preoperative and postoperative traumatic coagulopathy (PPTIC) in patients with trauma. Objective: This study aims to help clinicians implement timely and appropriate interventions to reduce the incidence of PPTIC and related complications, thereby lowering in-hospital mortality and disability rates for patients with trauma. Methods: We analyzed data from 13,235 patients with trauma from 4 medical centers, including medical histories, laboratory results, and hospitalization complications. We developed 10 ML models in Python (Python Software Foundation) to predict PPTIC based on preoperative indicators. Data from 10,023 Medical Information Mart for Intensive Care patients were divided into training (70%) and test (30%) sets, with 3212 patients from 3 other centers used for external validation. Model performance was assessed with 5-fold cross-validation, bootstrapping, Brier score, and Shapley additive explanation values. Results: Univariate logistic regression identified PPTIC risk factors as (1) prolonged activated partial thromboplastin time, prothrombin time, and international normalized ratio; (2) decreased levels of hemoglobin, hematocrit, red blood cells, calcium, and sodium; (3) lower admission diastolic blood pressure; (4) elevated alanine aminotransferase and aspartate aminotransferase levels; (5) admission heart rate; and (6) emergency surgery and perioperative transfusion. Multivariate logistic regression revealed that patients with PPTIC faced significantly higher 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), and urinary tract infection (1.95-fold), along with longer hospital and intensive care unit stays. Random forest was the most effective ML model for predicting PPTIC, achieving an area under the receiver operating characteristic of 0.91, an area under the precision-recall curve of 0.89, accuracy of 0.84, sensitivity of 0.80, specificity of 0.88, precision of 0.88, F1-score of 0.84, and Brier score of 0.13 in external validation. Conclusions: Key PPTIC risk factors include (1) prolonged activated partial thromboplastin time, prothrombin time, and international normalized ratio; (2) low levels of hemoglobin, hematocrit, red blood cells, calcium, and sodium; (3) low diastolic blood pressure; (4) elevated alanine aminotransferase and aspartate aminotransferase levels; (5) admission heart rate; and (6) the need for emergency surgery and transfusion. PPTIC is associated with severe complications and extended hospital stays. Among the ML models, the random forest model was the most effective predictor. Trial Registration: Chinese Clinical Trial Registry ChiCTR2300078097; https://www.chictr.org.cn/showproj.html?proj=211051

Neuropathic pain (NP) is caused by primary damage and dysfunction of nervous system, in which spinal cord injury (SCI) is a common cause of NP. Evidence shows that neuroinflammation and oxidative stress are related to the pathophysiology of NP, in which the activation of microglia and astrocytes in spinal is significant. Therefore, understanding the molecular mechanism of NP after SCI is of great significance. The rat model of SCI was established and BV2 cell was treated with LPS. The exosomes derived from astrocytes were extracted by centrifugation. The morphology of the exosomes was observed by electron microscope and the surface markers were detected by Western blot. LncRNA in astrocytes and astrocyte-derived exosomes were detected by qRT-PCR. The expression of microglia activation markers CD68 and Iba-1 was detected by immunohistochemistry. The von Frey test was applied to assess mechanical hypersensitivity. The heat plate analgesia instrument was used to evaluate Paw withdrawal latency (PWL). QRT-PCR used to detect expression of LncRNA49rik and miR-10a-5p. Western blot was used to detect MAPK/PI3K/AKT / mTOR signal pathway and COX2, iNOS. The content of MDA and the activity of SOD were detected by oxidative stress kit. The concentrations of IL-6, IL-1β, IL-18 and IFN-αwere detected by ELISA. The targeting relationship between LncRNA49rik and miR-10a-5p was analyzed by bioinformatics and double luciferase activity, Rip and FISH experiments. LncRNA49rik was highly expressed in astrocytes and its derived exosomes. SCI stimulated astrocytes to release exosome containing LncRNA49rik and promote microglia activation to increase inflammatory response. At the same time, overexpression of LncRNA49rik increased the incidence of NP and aggravated the level of inflammation and oxidative stress in rats with SCI. MiR-10a-5p is the target of LncRNA4933431K23Rik. Overexpression of LncRNA49rik significantly inhibited the up-regulation of miR-10a-5p. Overexpression of miR-10a-5p inhibited hyperalgesia and inflammation in SCI rats. In addition, transfection of miR-10a-5p mimics significantly inhibited the expression of MAPK/PI3K/AKT and up-regulated the expression of mTOR. Mechanism studies have shown that overexpression of miR-10a-5p weakens the phenotypic induction of microglia induced by LncRNA4933431K23Rik. LncRNA4933431K23Rik regulates microglial phenotype through inhibiting miR-10a-5p, which is responsible for NP induced by SCI.