Rapid referral of traumatic brain injury (TBI) patients requiring emergency neurosurgery to a specialized trauma center can significantly reduce morbidity and mortality. Currently, no model has been reported to predict the need for acute neurosurgery in severe to moderate TBI patients. This study aims to evaluate the performance of Machine Learning-based models to establish to predict the need for neurosurgery procedure within 24 h after moderate to severe TBI. Retrospective multicenter cohort study using data from a national trauma registry (Traumabase®) from November 2011 to December 2020. Inclusion criteria correspond to patients over 18 years old with moderate or severe TBI (Glasgow coma score ≤ 12) during prehospital assessment. Patients who died within the first 24 h after hospital admission and secondary transfers were excluded. The population was divided into a train set (80% of patients) and a test set (20% of patients). Several approaches were used to define the best prognostic model (linear nearest neighbor or ensemble model). The Shapley Value was used to identify the most relevant pre-hospital variables for prediction. 2159 patients were included in the study. 914 patients (42%) required neurosurgical intervention within 24 h. The population was predominantly male (77%), young (median age 35 years [IQR 24–52]) with severe head injury (median GCS 6 [3–9]). Based on the evaluation of the predictive model on the test set, the logistic regression model had an AUC of 0.76. The best predictive model was obtained with the CatBoost technique (AUC 0.81). According to the Shapley values method, the most predictive variables in the CatBoost were a low initial Glasgow coma score, the regression of pupillary abnormality after osmotherapy, a high blood pressure and a low heart rate. Machine learning-based models could predict the need for emergency neurosurgery within 24 h after moderate and severe head injury. Potential clinical benefits of such models as a decision-making tool deserve further assessment. The performance in real-life setting and the impact on clinical decision-making of the model requires workflow integration and prospective assessment.

中文翻译：

---

基于机器学习的中度至重度颅脑损伤后 24 小时内急诊神经外科手术预测

将需要紧急神经外科手术的创伤性脑损伤 (TBI) 患者快速转诊到专门的创伤中心可以显着降低发病率和死亡率。目前，尚无模型可预测重度至中度 TBI 患者是否需要急性神经外科手术。本研究旨在评估基于机器学习的模型的性能，以建立预测中度至重度 TBI 后 24 小时内神经外科手术的需要。回顾性多中心队列研究使用了 2011 年 11 月至 2020 年 12 月来自国家创伤登记处 (Traumabase®) 的数据。纳入标准对应于院前评估期间患有中度或重度 TBI（格拉斯哥昏迷评分 ≤ 12）的 18 岁以上患者。入院和二次转院后24小时内死亡的患者被排除在外。将人群分为训练组（80% 的患者）和测试组（20% 的患者）。几种方法用于定义最佳预后模型（线性最近邻或集成模型）。Shapley 值用于识别最相关的院前变量以进行预测。2159 名患者被纳入研究。914 名患者 (42%) 在 24 小时内需要神经外科干预。人群主要是男性（77%），年轻（中位年龄 35 岁 [IQR 24-52]），头部严重受伤（中位 GCS 6 [3-9]）。基于对测试集上预测模型的评估，逻辑回归模型的 AUC 为 0.76。使用 CatBoost 技术（AUC 0.81）获得了最佳预测模型。根据 Shapley 值法，CatBoost 中最具预测性的变量是初始 Glasgow 昏迷评分低、渗透治疗后瞳孔异常的消退、高血压和低心率。基于机器学习的模型可以预测中度和重度头部受伤后 24 小时内是否需要紧急神经外科手术。此类模型作为决策工具的潜在临床益处值得进一步评估。现实生活环境中的性能和模型对临床决策的影响需要工作流程整合和前瞻性评估。此类模型作为决策工具的潜在临床益处值得进一步评估。现实生活环境中的性能和模型对临床决策的影响需要工作流程整合和前瞻性评估。此类模型作为决策工具的潜在临床益处值得进一步评估。现实生活环境中的性能和模型对临床决策的影响需要工作流程整合和前瞻性评估。