1Department of Neurosurgery, Warren Alpert Medical School of Brown University.
2Carney Institute for Brain Science, Brown University.
J Neurosurg. 2019 Feb 22;132(2):552-559. doi: 10.3171/2018.11.JNS182199. Print 2020 Feb 1.
Traumatic intracranial hemorrhage (tICH) is a significant source of morbidity and mortality in trauma patients. While prognostic models for tICH outcomes may assist in alerting clinicians to high-risk patients, previously developed models face limitations, including low accuracy, poor generalizability, and the use of more prognostic variables than is practical. This study aimed to construct a simpler and more accurate method of risk stratification for all tICH patients.
The authors retrospectively identified a consecutive series of 4110 patients admitted to their institution's level 1 trauma center between 2003 and 2013. For each admission, they collected the patient's sex, age, systolic blood pressure, blood alcohol concentration, antiplatelet/anticoagulant use, Glasgow Coma Scale (GCS) score, Injury Severity Score, presence of epidural hemorrhage, presence of subdural hemorrhage, presence of subarachnoid hemorrhage, and presence of intraparenchymal hemorrhage. The final study population comprised 3564 patients following exclusion of records with missing data. The dependent variable under study was patient death. A k-fold cross-validation was carried out with the best models selected via the Akaike Information Criterion. These models risk stratified the study partitions into grade I (< 1% predicted mortality), grade II (1%-10% predicted mortality), grade III (10%-40% predicted mortality), or grade IV (> 40% predicted mortality) tICH. Predicted mortalities were compared with actual mortalities within grades to assess calibration. Concordance was also evaluated. A final model was constructed using the entire data set. Subgroup analysis was conducted for each hemorrhage type.
Cross-validation demonstrated good calibration (p < 0.001 for all grades) with a mean concordance of 0.881 (95% CI 0.865-0.898). In the authors' final model, older age, lower blood alcohol concentration, antiplatelet/anticoagulant use, lower GCS score, and higher Injury Severity Score were all associated with greater mortality. Subgroup analysis showed successful stratification for subarachnoid, intraparenchymal, grade II-IV subdural, and grade I epidural hemorrhages.
The authors developed a risk stratification model for tICH of any GCS score with concordance comparable to prior models and excellent calibration. These findings are applicable to multiple hemorrhage subtypes and can assist in identifying low-risk patients for more efficient resource allocation, facilitate family conversations regarding goals of care, and stratify patients for research purposes. Future work will include testing of more variables, validation of this model across institutions, as well as creation of a simplified model whose outputs can be calculated mentally.
创伤性颅内出血（tICH）是创伤患者发病率和死亡率的重要来源。虽然用于预测 tICH 结局的预后模型可以帮助临床医生发现高风险患者，但以前开发的模型存在局限性，包括准确性低、通用性差以及使用的预后变量过多而不实用。本研究旨在构建一种更简单、更准确的方法对所有 tICH 患者进行风险分层。
作者回顾性地确定了 2003 年至 2013 年期间在他们机构的一级创伤中心入院的 4110 例连续患者。对于每次入院，他们收集了患者的性别、年龄、收缩压、血酒精浓度、抗血小板/抗凝药物使用、格拉斯哥昏迷评分（GCS）、损伤严重程度评分、硬膜外血肿、硬膜下血肿、蛛网膜下腔出血和脑实质血肿的存在情况。排除记录中缺失数据的记录后，最终研究人群包括 3564 例患者。研究的因变量为患者死亡。通过 Akaike 信息准则选择最佳模型进行了 k 折交叉验证。这些模型将研究分区分为 I 级（<1%预测死亡率）、II 级（1%-10%预测死亡率）、III 级（10%-40%预测死亡率）或 IV 级（>40%预测死亡率）tICH。比较了各等级内的预测死亡率与实际死亡率以评估校准情况。还评估了一致性。使用整个数据集构建了最终模型。对每种出血类型进行了亚组分析。
交叉验证表明校准良好（所有等级的 p<0.001），平均一致性为 0.881（95%置信区间 0.865-0.898）。在作者的最终模型中，年龄较大、血酒精浓度较低、抗血小板/抗凝药物使用、GCS 评分较低和损伤严重程度评分较高均与死亡率增加相关。亚组分析表明蛛网膜下腔出血、脑实质出血、II-IV 级硬膜下血肿和 I 级硬膜外血肿的分层均成功。
作者开发了一种任何 GCS 评分的 tICH 风险分层模型，其一致性可与先前的模型相媲美，且校准效果良好。这些发现适用于多种出血亚型，可以帮助识别低风险患者，从而更有效地分配资源，促进家庭讨论护理目标，并为研究目的分层患者。未来的工作将包括测试更多变量、在不同机构验证该模型以及创建一个简化的模型，其输出可以在头脑中计算。
