Department of Neurosurgery, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea.
Department of Neurosurgery, Gyeongsang National University Hospital, Gyeongsang National University School of Medicine, Jinju-Si, Gyeongsangnam-do, Republic of Korea.
World Neurosurg. 2022 Oct;166:e125-e134. doi: 10.1016/j.wneu.2022.06.130. Epub 2022 Jul 3.
Machine learning (ML) has been used to predict the outcomes of traumatic brain injury. However, few studies have reported the use of ML models to predict early death. This study aimed to develop ML models for early death prediction and to compare performance with the corticosteroid randomization after significant head injury (CRASH) model.
We retrospectively reviewed traumatic brain injury patients between February 2017 and August 2021. The patients were randomly assigned to a training set and a test set. Predictive variables included clinical findings, laboratory values, and computed tomography findings. The ML models (random forest, support vector machine [SVM], logistic regression) were developed with the training set. The CRASH model is a prognostic model that was developed based on 10,008 patients included in the CRASH trial. The ML and CRASH models were applied to the test set to evaluate the performance.
A total of 423 patients were included; 317 and 106 patients were randomly assigned to the training and test sets, respectively. The area under the curve was highest in the SVM (0.952, 95% confidence interval = 0.906-0.990) and lowest in the CRASH model (0.942, 95% confidence interval = 0.886-0.999). There were no significant differences between the area under the curves of the ML and CRASH models (P = 0.899 for random forest vs. the CRASH model, P = 0.760 for SVM vs. the CRASH model, P = 0.806 for logistic regression vs. the CRASH model).
The ML models may have comparable performances compared to the CRASH model despite being developed with a smaller sample size.
机器学习（ML）已被用于预测创伤性脑损伤的结果。然而，很少有研究报告使用 ML 模型来预测早期死亡。本研究旨在开发用于早期死亡预测的 ML 模型，并将其性能与颅脑损伤后皮质类固醇随机分组（CRASH）模型进行比较。
我们回顾性分析了 2017 年 2 月至 2021 年 8 月间的创伤性脑损伤患者。患者被随机分配到训练集和测试集。预测变量包括临床发现、实验室值和计算机断层扫描发现。使用训练集开发 ML 模型（随机森林、支持向量机[SVM]、逻辑回归）。CRASH 模型是基于 CRASH 试验中纳入的 10008 例患者开发的预后模型。将 ML 和 CRASH 模型应用于测试集以评估性能。
共纳入 423 例患者；317 例和 106 例患者被随机分配到训练集和测试集。SVM 的曲线下面积最高（0.952，95%置信区间为 0.906-0.990），CRASH 模型最低（0.942，95%置信区间为 0.886-0.999）。ML 和 CRASH 模型的曲线下面积无显著差异（随机森林与 CRASH 模型比较，P=0.899；SVM 与 CRASH 模型比较，P=0.760；逻辑回归与 CRASH 模型比较，P=0.806）。
尽管使用的样本量较小，但 ML 模型的性能可能与 CRASH 模型相当。
