Clinical Research, Trauma and Vascular Surgery, Hamad Medical Corporation, Doha, Qatar; Clinical Medicine, Weill Cornell Medical College, Doha, Qatar.
Clinical Research, Trauma and Vascular Surgery, Hamad Medical Corporation, Doha, Qatar.
Comput Biol Med. 2024 Sep;179:108880. doi: 10.1016/j.compbiomed.2024.108880. Epub 2024 Jul 16.
The effective management of trauma patients necessitates efficient triaging, timely activation of Massive Blood Transfusion Protocols (MTP), and accurate prediction of in-hospital outcomes. Machine learning (ML) algorithms have emerged as up-and-coming tools in the domains of optimizing triage decisions, improving intervention strategies, and predicting clinical outcomes, consistently outperforming traditional methodologies. This study aimed to develop, assess, and compare several ML models for the triaging processes, activation of MTP, and mortality prediction.
In a 10-year retrospective study, the predictive capabilities of seven ML models for trauma patients were systematically assessed using on-admission patients' hemodynamic data. All patient's data were randomly divided into training (80 %) and test (20 %) sets. Employing Python for data preprocessing, feature scaling, and model development, we evaluated K-Nearest Neighbors (KNN), Logistic Regression (LR), Decision Tree (DT), Support Vector Machines (SVM) with RBF kernels, Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Artificial Neural Network (ANN). We employed various imputation techniques and addressed data imbalance through down-sampling, up-sampling, and synthetic minority for the over-sampling technique (SMOTE). Hyperparameter tuning, coupled with 5-fold cross-validation, was performed. The evaluation included essential metrics like sensitivity, specificity, F1 score, accuracy, Area Under the Receiver Operating Curve (AUC ROC), and Area Under the Precision recall Curve (AUC PR), ensuring robust predictive capability.
This study included 17,390 adult trauma patients; of them, 19.5 % (3385) were triaged at a critical level, 3.8 % (664) required MTP, and 7.7 % (1335) died in the hospital. The model's performance improved using imputation and balancing techniques. The overall models demonstrated notable performance metrics for predicting triage, MTP activation, and mortality with F1 scores of 0.75, 0.42, and 0.79, sensitivities of 0.73, 0.82, and 0.9, and AUC ROC values of 0.89, 0.95 and 0.99 respectively.
Machine learning, especially RF models, effectively predicted trauma triage, MTP activation, and mortality. Featured critical hemodynamic variables include shock indices, systolic blood pressure, and mean arterial pressure. Therefore, models can do better than individual parameters for the early management and disposition of patients in the ED. Future research should focus on creating sensitive and interpretable models to enhance trauma care.
有效管理创伤患者需要高效分诊、及时启动大量输血方案 (MTP) 以及准确预测院内结局。机器学习 (ML) 算法已成为优化分诊决策、改进干预策略和预测临床结局的新兴工具，其表现始终优于传统方法。本研究旨在开发、评估和比较用于分诊流程、MTP 激活和死亡率预测的几种 ML 模型。
在一项回顾性的 10 年研究中，我们使用入院时患者的血流动力学数据，系统地评估了七种 ML 模型对创伤患者的预测能力。所有患者的数据均随机分为训练 (80%) 和测试 (20%) 集。我们使用 Python 进行数据预处理、特征缩放和模型开发，评估了 K-最近邻 (KNN)、逻辑回归 (LR)、决策树 (DT)、具有 RBF 核的支持向量机 (SVM)、随机森林 (RF)、极端梯度提升 (XGBoost) 和人工神经网络 (ANN)。我们采用了多种插补技术，并通过下采样、上采样和过采样技术中的合成少数 (SMOTE) 来解决数据不平衡问题。进行了超参数调整，并结合 5 折交叉验证。评估包括灵敏度、特异性、F1 评分、准确性、接收器操作特征曲线下面积 (AUC ROC) 和精度召回曲线下面积 (AUC PR) 等重要指标，以确保稳健的预测能力。
本研究纳入了 17390 例成年创伤患者；其中 19.5% (3385 例) 分诊为危急级别，3.8% (664 例) 需要 MTP，7.7% (1335 例) 院内死亡。使用插补和平衡技术后，模型性能得到了提高。总体模型在预测分诊、MTP 激活和死亡率方面表现出优异的性能指标，F1 评分分别为 0.75、0.42 和 0.79，灵敏度分别为 0.73、0.82 和 0.9，AUC ROC 值分别为 0.89、0.95 和 0.99。
机器学习，特别是 RF 模型，可有效预测创伤分诊、MTP 激活和死亡率。特征性关键血流动力学变量包括休克指数、收缩压和平均动脉压。因此，对于 ED 中患者的早期管理和处置，模型的表现优于单个参数。未来的研究应侧重于创建敏感且可解释的模型，以提高创伤护理水平。
