St. Christopher's Hospital for Children, Department of Pediatric General Thoracic, and Minimally Invasive Surgery, Philadelphia, PA 19134, USA.
St. Christopher's Hospital for Children, Department of Pediatric General Thoracic, and Minimally Invasive Surgery, Philadelphia, PA 19134, USA.
J Pediatr Surg. 2023 Jun;58(6):1200-1205. doi: 10.1016/j.jpedsurg.2023.02.040. Epub 2023 Feb 18.
Venous thromboembolism (VTE) causes significant morbidity in pediatric trauma patients. We applied machine learning algorithms to the Trauma Quality Improvement Program (TQIP) database to develop and validate a risk prediction model for VTE in injured children.
Patients ≤18 years were identified from TQIP (2017-2019, n = 383,814). Those administered VTE prophylaxis ≤24 h and missing the outcome (VTE) were removed (n = 347,576). Feature selection identified 15 predictors: intubation, need for supplemental oxygen, spinal injury, pelvic fractures, multiple long bone fractures, major surgery (neurosurgery, thoracic, orthopedic, vascular), age, transfusion requirement, intracranial pressure monitor or external ventricular drain placement, and low Glasgow Coma Scale score. Data was split into training (n = 251,409) and testing (n = 118,175) subsets. Machine learning algorithms were trained, tested, and compared.
Low-risk prediction: For the testing subset, all models outperformed the baseline rate of VTE (0.15%) with a predicted rate of 0.01-0.02% (p < 2.2e). 88.4-89.4% of patients were classified as low risk by the models.
HIGH-RISK PREDICTION: All models outperformed baseline with a predicted rate of VTE ranging from 1.13 to 1.32% (p < 2.2e). The performance of the 3 models was not significantly different.
We developed a predictive model that differentiates injured children for development of VTE with high discrimination and can guide prophylaxis use.
Prognostic, Level II.
Retrospective, Cross-sectional.
静脉血栓栓塞症（VTE）会给儿科创伤患者带来严重的发病率。我们将机器学习算法应用于创伤质量改进计划（TQIP）数据库，以开发和验证受伤儿童 VTE 的风险预测模型。
从 TQIP（2017-2019 年，n=383814）中确定≤18 岁的患者。去除在 24 小时内给予 VTE 预防且未发生结局（VTE）的患者（n=347576）。特征选择确定了 15 个预测因素：插管、需要补充氧气、脊柱损伤、骨盆骨折、多处长骨骨折、大手术（神经外科、胸外科、矫形外科、血管外科）、年龄、输血需求、颅内压监测或外部脑室引流管放置以及格拉斯哥昏迷量表评分低。数据分为训练集（n=251409）和测试集（n=118175）。训练、测试和比较了机器学习算法。
低风险预测：对于测试集，所有模型的 VTE 预测率均优于基线率（0.15%），预测率为 0.01-0.02%（p<2.2e）。88.4%-89.4%的患者被模型归类为低风险。
所有模型的 VTE 预测率均优于基线，范围为 1.13%至 1.32%（p<2.2e）。3 种模型的性能没有显著差异。
我们开发了一种预测模型，可以区分易发生 VTE 的受伤儿童，并指导预防用药。
预后，II 级。
回顾性，横断面。
