使用机器学习算法预测重型创伤性脑损伤后的颅内压危象
本研究回顾性纳入36例重型TBI(GCS<8)患者,利用连续颅内压监测数据训练机器学习模型预测颅内压危象(ICP>22 mm Hg持续至少5分钟区间的75%数据)。随机森林模型在四组数据集上准确度0.82-0.88、AUC 0.86-0.88,验证集精确率0.76、召回率0.46、F1 0.57、准确度0.86,可提前10-20分钟预测危象。
要点
- 随机森林模型在四组数据集上准确度0.82-0.88、AUC 0.86-0.88。
- 验证集精确率0.76、召回率0.46、F1 0.57、准确度0.86。
- 模型可提前10-20分钟预测重型TBI患者的颅内压危象。
核心结论
- 所提出的模型可在颅内压危象发生前10-20分钟对重型TBI患者提供准确及时的预测。
- 若经验证并整合入临床工作流程,该算法可促成更早干预颅内压危象、更有效治疗颅内高压,并可能改善重型TBI后的结局。
研究设计与样本
- 回顾性识别2015年4月至2019年1月间入住一级创伤中心、GCS评分<8且接受连续脑实质颅内压监测的36例重型TBI患者。
- 从每个监测时段(监测时长范围4-96小时)提取连续颅内压数据。
- 颅内压危象定义为5分钟区间内至少75%的数据颅内压>22 mm Hg的二分类结局。
- 将每次颅内压危象前的数据分为四组数据集,分别为1小时和2小时时段,每组均含危象前10-20分钟的前置时间间隔。
- 从30例患者子集中识别危象与非危象事件,随机按70%训练、30%测试划分;训练轻梯度提升、极端梯度提升和随机森林算法,以准确度和受试者工作特征曲线下面积(AUC)比较性能。
主要发现
- 随机森林模型在全部四组数据集上准确度最高(范围0.82-0.88),AUC最高(范围0.86-0.88)。
- 进一步验证测试显示精确率高(0.76)、召回率相对较低(0.46),对颅内压危象总体预测性能强(F1分数0.57,准确度0.86)。
- 决策曲线分析显示模型在概率阈值高于0.1且低于0.9时提供净获益。
临床怎么用
- 原文结论指出,若经验证并整合入临床工作流程,该算法可促成更早干预颅内压危象、更有效治疗颅内高压,并可能改善重型TBI后的结局。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
OBJECTIVE: Avoiding intracranial hypertension after traumatic brain injury (TBI) is a foundation of neurocritical care, to minimize secondary brain injury related to elevated intracranial pressure (ICP). However, this approach at best is reactive to episodes of intracranial hypertension, allowing for periods of elevated ICP before therapies can be initiated. Accurate prediction of ICP crises before they occur would permit clinicians to implement preventive strategies, minimize total time with ICP above threshold, and potentially avoid secondary injury. The objective of this study was to develop an algorithm capable of predicting the onset of ICP crises with sufficient lead time to enable application of preventative therapies. METHODS: Thirty-six patients admitted to a level I trauma center with severe TBI (Glasgow Coma Scale score < 8) between April 2015 and January 2019 who underwent continuous intraparenchymal ICP monitor placement were retrospectively identified. Continuous ICP data were extracted from each monitoring period (range 4-96 hours of monitoring). An ICP crisis was treated as a binary outcome, defined as ICP > 22 mm Hg for at least 75% of the data within a 5-minute interval. ICP data preceding each ICP crisis were grouped into four total data sets of 1- and 2-hour epochs, each with 10- to 20-minute lead-time intervals before an ICP crisis. Crisis and noncrisis events were identified from continuous time-series data and randomly split into 70% for training and 30% for testing, from a subset of 30 patients. Machine learning algorithms were trained to predict ICP crises, including light gradient boosting, extreme gradient boosting, and random forest. Accuracy and area under the receiver operating characteristic curve (AUC) were measured to compare performance. The most predictive algorithm was optimized using feature selection and hyperparameter tuning to avoid overfitting, and then tested on a validation subset of 5 patients. Precision, recall, F1 score, and accuracy were measured. RESULTS: The random forest model demonstrated the highest accuracy (range 0.82-0.88) and AUC (range 0.86-0.88) across all four data sets. Further validation testing revealed high precision (0.76), relatively low recall (0.46), and overall strong predictive performance (F1 score 0.57, accuracy 0.86) for ICP crises. Decision curve analysis showed that the model provided net benefit at probability thresholds above 0.1 and below 0.9. CONCLUSIONS: The presented model can provide accurate and timely forecasts of ICP crises in patients with severe TBI 10-20 minutes prior to their occurrence. If validated and implemented in clinical workflows, this algorithm can enable earlier intervention for ICP crises, more effective treatment of intracranial hypertension, and potentially improved outcomes following severe TBI.
引用
- Petrov D, Miranda SP, Balu R, et al. Prediction of intracranial pressure crises after severe traumatic brain injury using machine learning algorithms. J Neurosurg. 2023. PMID: 36708534. doi:10.3171/2022.12.JNS221860
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。