Xiong Xiaojuan, Fu Hong, Xu Bo, Wei Wang, Zhou Mi, Hu Peng, Ren Yunqin, Mao Qingxiang
Department of Anesthesiology, Daping Hospital, Army Medical University, Chongqing, China.
Department of Anesthesiology, Chongqing Emergency Medical Center, Chongqing University Central Hospital, School of Medicine, Chongqing University, Chongqing, China.
J Med Internet Res. 2025 Jan 22;27:e66612. doi: 10.2196/66612.
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.
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.
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.
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, F-score of 0.84, and Brier score of 0.13 in external validation.
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.
Chinese Clinical Trial Registry ChiCTR2300078097; https://www.chictr.org.cn/showproj.html?proj=211051.
最近的研究揭示了机器学习（ML）模型在改善创伤患者预后预测方面的潜在价值。ML可以增强预测能力，并确定哪些因素对创伤后死亡率的影响最大。然而，尚无研究探讨创伤患者术前和术后创伤性凝血病（PPTIC）的危险因素、并发症及风险预测。
本研究旨在帮助临床医生实施及时、恰当的干预措施，以降低PPTIC的发生率及相关并发症，从而降低创伤患者的院内死亡率和残疾率。
我们分析了来自4个医疗中心的13235例创伤患者的数据，包括病史、实验室检查结果及住院并发症。我们在Python（Python软件基金会）中开发了10个ML模型，以根据术前指标预测PPTIC。来自重症监护医学信息集市的10023例患者的数据被分为训练集（70%）和测试集（30%），另外3个中心的3212例患者用于外部验证。通过5折交叉验证、自助法、Brier评分和Shapley相加解释值评估模型性能。
单因素逻辑回归确定PPTIC的危险因素为：（1）活化部分凝血活酶时间、凝血酶原时间和国际标准化比值延长；（2）血红蛋白、血细胞比容、红细胞、钙和钠水平降低；（3）入院时舒张压降低；（4）丙氨酸氨基转移酶和天冬氨酸氨基转移酶水平升高；（5）入院心率；（6）急诊手术和围手术期输血。多因素逻辑回归显示，PPTIC患者发生脓毒症（1.75倍）、心力衰竭（1.5倍）、谵妄（3.08倍）、凝血异常（3.57倍）、气管切开（2.76倍）、死亡（2.19倍）和尿路感染（1.95倍）的风险显著更高，住院时间和重症监护病房停留时间更长。随机森林是预测PPTIC最有效的ML模型，在外部验证中，受试者操作特征曲线下面积为0.91，精确召回率曲线下面积为0.89，准确率为0.84，灵敏度为0.80，特异度为0.88，精确率为0.88，F值为0.84，Brier评分为0.13。
PPTIC的关键危险因素包括：（1）活化部分凝血活酶时间、凝血酶原时间和国际标准化比值延长；（2）血红蛋白、血细胞比容、红细胞、钙和钠水平低；（3）舒张压低；（4）丙氨酸氨基转移酶和天冬氨酸氨基转移酶水平升高；（5）入院心率；（6）急诊手术和输血需求。PPTIC与严重并发症和延长住院时间相关。在ML模型中，随机森林模型是最有效的预测模型。
中国临床试验注册中心ChiCTR2300078097；https://www.chictr.org.cn/showproj.html?proj=211051 。
