Data_Sheet_1_A Machine Learning Approach for the Prediction of Traumatic Brain Injury Induced Coagulopathy.docx

Background: Traumatic brain injury-induced coagulopathy (TBI-IC), is a disease with poor prognosis and increased mortality rate.Objectives: Our study aimed to identify predictors as well as develop machine learning (ML) models to predict the risk of coagulopathy in this population.Methods: ML models were developed and validated based on two public databases named Medical Information Mart for Intensive Care (MIMIC)-IV and the eICU Collaborative Research Database (eICU-CRD). Candidate predictors, including demographics, family history, comorbidities, vital signs, laboratory findings, injury type, therapy strategy and scoring system were included. Models were compared on area under the curve (AUC), accuracy, sensitivity, specificity, positive and negative predictive values, and decision curve analysis (DCA) curve.Results: Of 999 patients in MIMIC-IV included in the final cohort, a total of 493 (49.35%) patients developed coagulopathy following TBI. Recursive feature elimination (RFE) selected 15 variables, including international normalized ratio (INR), prothrombin time (PT), sepsis related organ failure assessment (SOFA), activated partial thromboplastin time (APTT), platelet (PLT), hematocrit (HCT), red blood cell (RBC), hemoglobin (HGB), blood urea nitrogen (BUN), red blood cell volume distribution width (RDW), creatinine (CRE), congestive heart failure, myocardial infarction, sodium, and blood transfusion. The external validation in eICU-CRD demonstrated that adapting boosting (Ada) model had the highest AUC of 0.924 (95% CI: 0.902–0.943). Furthermore, in the DCA curve, the Ada model and the extreme Gradient Boosting (XGB) model had relatively higher net benefits (ie, the correct classification of coagulopathy considering a trade-off between false- negatives and false-positives)—over other models across a range of threshold probability values.Conclusions: The ML models, as indicated by our study, can be used to predict the incidence of TBI-IC in the intensive care unit (ICU).

背景：由脑外伤引起的凝血功能障碍（TBI-IC）是一种预后不良、死亡率增高的疾病。研究目的：本研究旨在识别预测因素，并开发机器学习（ML）模型以预测该人群凝血功能障碍的风险。方法：基于两个公开数据库——重症监护医疗信息市场（MIMIC）-IV和电子重症监护协作研究数据库（eICU-CRD）——开发并验证了机器学习模型。候选预测因素包括人口统计学、家族史、合并症、生命体征、实验室检查结果、损伤类型、治疗策略和评分系统。模型在曲线下面积（AUC）、准确率、灵敏度、特异性、阳性预测值、阴性预测值以及决策曲线分析（DCA）曲线等方面进行了比较。结果：在最终队列中，包括MIMIC-IV的999名患者中，共有493名（49.35%）患者在脑外伤后发生了凝血功能障碍。递归特征消除（RFE）选出了15个变量，包括国际标准化比率（INR）、凝血酶原时间（PT）、与脓毒症相关的器官功能衰竭评估（SOFA）、活化部分凝血活酶时间（APTT）、血小板（PLT）、红细胞压积（HCT）、红细胞（RBC）、血红蛋白（HGB）、血尿素氮（BUN）、红细胞体积分布宽度（RDW）、肌酐（CRE）、充血性心力衰竭、心肌梗死、钠和输血。在eICU-CRD中的外部验证显示，自适应提升（Ada）模型具有最高的AUC（0.924，95% CI：0.902–0.943）。此外，在DCA曲线上，Ada模型和极端梯度提升（XGB）模型在一系列阈值概率值范围内相对于其他模型具有相对较高的净收益（即，在假阴性与假阳性之间的权衡下正确分类凝血功能障碍）。结论：根据本研究，机器学习模型可用于预测重症监护病房（ICU）中TBI-IC的发生率。