Department of Emergency Medicine, Korea University Anam Hospital, Seoul, Republic of Korea.
Department of Emergency Medicine, Seoul National University Hospital, Seoul, Republic of Korea.
J Neurotrauma. 2023 Jul;40(13-14):1376-1387. doi: 10.1089/neu.2022.0280. Epub 2023 Mar 14.
Traumatic brain injury (TBI) is a significant healthcare concern in several countries, accounting for a major burden of morbidity, mortality, disability, and socioeconomic losses. Although conventional prognostic models for patients with TBI have been validated, their performance has been limited. Therefore, we aimed to construct machine learning (ML) models to predict the clinical outcomes in adult patients with isolated TBI in Asian countries. The Pan-Asian Trauma Outcome Study registry was used in this study, and the data were prospectively collected from January 1, 2015, to December 31, 2020. Among a total of 6540 patients (≥ 15 years) with isolated moderate and severe TBI, 3276 (50.1%) patients were randomly included with stratification by outcomes and subgrouping variables for model evaluation, and 3264 (49.9%) patients were included for model training and validation. Logistic regression was considered as a baseline, and ML models were constructed and evaluated using the area under the precision-recall curve (AUPRC) as the primary outcome metric, area under the receiver operating characteristic curve (AUROC), and precision at fixed levels of recall. The contribution of the variables to the model prediction was measured using the SHapley Additive exPlanations (SHAP) method. The ML models outperformed logistic regression in predicting the in-hospital mortality. Among the tested models, the gradient-boosted decision tree showed the best performance (AUPRC, 0.746 [0.700-0.789]; AUROC, 0.940 [0.929-0.952]). The most powerful contributors to model prediction were the Glasgow Coma Scale, O saturation, transfusion, systolic and diastolic blood pressure, body temperature, and age. Our study suggests that ML techniques might perform better than conventional multi-variate models in predicting the outcomes among adult patients with isolated moderate and severe TBI.
创伤性脑损伤（TBI）是多个国家重要的医疗保健关注点，是发病率、死亡率、残疾和社会经济损失的主要原因。虽然已经验证了用于 TBI 患者的传统预后模型，但它们的性能有限。因此，我们旨在构建机器学习（ML）模型来预测亚洲国家成人孤立性 TBI 患者的临床结局。本研究使用了泛亚创伤结局研究登记处的数据，这些数据是从 2015 年 1 月 1 日至 2020 年 12 月 31 日期间前瞻性收集的。在总共 6540 名（≥15 岁）患有中度和重度孤立性 TBI 的患者中，3276 名（50.1%）患者被随机纳入，根据结局和亚组变量进行分层，用于模型评估，3264 名（49.9%）患者被纳入模型训练和验证。逻辑回归被认为是基线，使用精度-召回率曲线下面积（AUPRC）作为主要结果指标、接受者操作特征曲线下面积（AUROC）和在固定召回水平的精度构建和评估 ML 模型。使用 SHapley Additive exPlanations（SHAP）方法衡量变量对模型预测的贡献。在预测住院死亡率方面，ML 模型优于逻辑回归。在测试的模型中，梯度提升决策树表现最佳（AUPRC，0.746 [0.700-0.789]；AUROC，0.940 [0.929-0.952]）。对模型预测贡献最大的因素是格拉斯哥昏迷量表、氧饱和度、输血、收缩压和舒张压、体温和年龄。我们的研究表明，与传统的多变量模型相比，机器学习技术在预测成人中度和重度孤立性 TBI 患者的结局方面可能表现更好。
