基于颅内压数据使用机器学习算法预测创伤性脑损伤的严重程度和出院预后
本研究基于单中心前瞻性收集的神经外科重症监护病房入院患者队列,提取术后前6小时颅内压相关数据,用机器学习算法预测创伤性脑损伤严重程度(术后第一天格拉斯哥昏迷量表评分)和短期预后(出院时格拉斯哥结局扩展量表评分)。仅用平均颅内压的 logistic 回归模型预测能力有限(AUC 0.558),而结合颅内压相关数据均值与复杂度指标的多变量随机森林模型预测能力最强(AUC 0.815),预测出院格拉斯哥结局扩展量表评分的 AUC 为 0.822。
要点
- 仅用平均颅内压的 logistic 回归模型预测创伤性脑损伤严重程度能力有限,AUC 为 0.558。
- 结合颅内压数据均值与复杂度指标的随机森林模型预测严重程度能力最强,AUC 为 0.815。
- 该随机森林模型预测出院格拉斯哥结局扩展量表评分的 AUC 为 0.822,交叉验证证实其性能。
核心结论
- 结合颅内压数据均值与复杂度指标的随机森林模型在准确预测创伤性脑损伤严重程度和短期预后方面具有临床实用性。
研究设计与样本
- 单中心前瞻性收集的神经外科重症监护病房入院患者队列,提取术后前6小时颅内压相关数据并用复杂算法处理。
- 以术后第一天格拉斯哥昏迷量表评分和出院时格拉斯哥结局扩展量表评分作为二分类结局变量。
- 构建仅用平均颅内压值的单变量 logistic 回归模型,以及3个使用不同组合的均值与复杂度指标的多变量随机森林模型。
- 采用五折交叉验证以避免过拟合。
主要发现
- 仅用平均颅内压值的 logistic 回归模型预测能力有限,AUC 为 0.558。
- 结合颅内压相关数据均值与复杂度指标的随机森林模型预测能力最稳健,AUC 为 0.815。
- 该模型预测出院格拉斯哥结局扩展量表评分的性能一致,AUC 为 0.822。
- 交叉验证分析证实了模型性能。
临床怎么用
- 原文未据此给出推荐。
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: This study aimed to explore the potential of employing machine learning algorithms based on intracranial pressure (ICP), ICP-derived parameters, and their complexity to predict the severity and short-term prognosis of traumatic brain injury (TBI). METHODS: A single-center prospectively collected cohort of neurosurgical intensive care unit admissions was analyzed. We extracted ICP-related data within the first 6 hours and processed them using complex algorithms. To indicate TBI severity and short-term prognosis, Glasgow Coma Scale score on the first postoperative day and Glasgow Outcome Scale-Extended score at discharge were used as binary outcome variables. A univariate logistic regression model was developed to predict TBI severity using only mean ICP values. Subsequently, 3 multivariate Random Forest (RF) models were constructed using different combinations of mean and complexity metrics of ICP-related data. To avoid overfitting, five-fold cross-validations were performed. Finally, the best-performing multivariate RF model was used to predict patients' discharge Glasgow Outcome Scale-Extended score. RESULTS: The logistic regression model exhibited limited predictive ability with an area under the curve (AUC) of 0.558. Among multivariate models, the RF model, combining the mean and complexity metrics of ICP-related data, achieved the most robust ability with an AUC of 0.815. Finally, in terms of predicting discharge Glasgow Outcome Scale-Extended score, this model had a consistent performance with an AUC of 0.822. Cross-validation analysis confirmed the performance. CONCLUSIONS: This study demonstrates the clinical utility of the RF model, which integrates the mean and complexity metrics of ICP data, in accurately predicting the TBI severity and short-term prognosis.
引用
- Zhu J, Shan Y, Li Y, et al. Predicting the Severity and Discharge Prognosis of Traumatic Brain Injury Based on Intracranial Pressure Data Using Machine Learning Algorithms. World Neurosurg. 2024. PMID: 38519020. doi:10.1016/j.wneu.2024.03.085
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。