文献速递重症综合管理与镇静镇痛心脑血管急症

基于机器学习的重型颅脑创伤神经重症监护中颅内压不良事件临近预测

Machine Learning Based Prediction of Imminent ICP Insults During Neurocritical Care of Traumatic Brain Injury.
PubMed 文献 · Neurocrit Care · 2024-09-25
一句话结论在602例TBI患者138,411小时监测数据中,XGBoost等AI模型预测30分钟内颅内压不良事件,灵敏度94.1%、特异度94.6%、AUROC 98.8%。

本研究使用Uppsala高频TBI数据集,训练高斯过程回归、逻辑回归、随机森林与XGBoost四类模型,预测30分钟内将出现的颅内压不良事件,并比较仅用监测数据与加入临床、人口学及影像学数据后的表现。共纳入602例TBI患者,总监测138,411小时。高斯过程回归模型灵敏度93.2%、特异度93.9%、AUROC 98.3%;XGBoost灵敏度93.8%、特异度94.6%、AUROC 98.7%;加入更多临床变量后XGBoost灵敏度94.1%、特异度94.6%、AUROC 98.8%。作者认为AI模型有潜力成为神经重症监护中提前预测颅内压不良事件的工具。

要点

  • XGBoost加入临床变量后预测30分钟内颅内压不良事件:灵敏度94.1%、特异度94.6%、AUROC 98.8%。
  • 仅用监测数据的XGBoost:灵敏度93.8%、特异度94.6%、AUROC 98.7%。
  • 高斯过程回归模型:灵敏度93.2%、特异度93.9%、AUROC 98.3%,与既往较小研究表现相似。
  • 研究基于Uppsala高频TBI数据集,共602例TBI患者、总监测138,411小时。
  • 作者认为AI模型有潜力成为神经重症监护中提前预测颅内压不良事件的工具。

适用人群与场景

  • 重症监护中接受颅内压监测的创伤性颅脑损伤(TBI)患者,数据来自Uppsala高频TBI数据集,共602例,总监测138,411小时。

研究设计与关键结果

  • 研究类型:基于Uppsala高频TBI数据集的模型开发与性能比较研究,纳入602例TBI患者,总监测138,411小时。
  • 预测任务:预测30分钟内将开始的颅内压不良事件;分别使用仅含监测数据的限制数据集和加入临床数据、人口学数据及影像学评估的无限制数据集。
  • 比较四类模型:高斯过程回归、逻辑回归、随机森林分类器、Extreme Gradient Boosted决策树(XGBoost)。
  • 高斯过程回归模型在Uppsala高频TBI数据集上:灵敏度93.2%、特异度93.9%、AUROC 98.3%,与既往较小研究表现相似。
  • XGBoost模型:灵敏度93.8%、特异度94.6%、AUROC 98.7%。
  • 加入更多临床变量和特征后XGBoost表现略有提升:灵敏度94.1%、特异度94.6%、AUROC 98.8%。

证据类型、等级与局限

  • 证据类型:基于高频TBI监测数据集的模型开发与性能比较研究。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为人工智能模型有潜力成为神经重症监护中提前预测颅内压不良事件的工具。
  • 作者指出,常用现成模型如XGBoost在预测颅内压不良事件上表现良好,这为该领域更快进展和更早临床实施提供了新可能。

提炼说明

  • 本条依据论文摘要整理;摘要未涉及「诊断标准与关键阈值」「处置流程与药物剂量」「红旗征与不能漏的情况」「指南或共识出处」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开

BACKGROUND: In neurointensive care, increased intracranial pressure (ICP) is a feared secondary brain insult in traumatic brain injury (TBI). A system that predicts ICP insults before they emerge may facilitate early optimization of the physiology, which may in turn lead to stopping the predicted ICP insult from occurring. The aim of this study was to evaluate the performance of different artificial intelligence models in predicting the risk of ICP insults.

METHODS: The models were trained to predict risk of ICP insults starting within 30 min, using the Uppsala high frequency TBI dataset. A restricted dataset consisting of only monitoring data were used, and an unrestricted dataset using monitoring data as well as clinical data, demographic data, and radiological evaluations was used. Four different model classes were compared: Gaussian process regression, logistic regression, random forest classifier, and Extreme Gradient Boosted decision trees (XGBoost).

RESULTS: Six hundred and two patients with TBI were included (total monitoring 138,411 h). On the task of predicting upcoming ICP insults, the Gaussian process regression model performed similarly on the Uppsala high frequency TBI dataset (sensitivity 93.2%, specificity 93.9%, area under the receiver operating characteristic curve [AUROC] 98.3%), as in earlier smaller studies. Using a more flexible model (XGBoost) resulted in a comparable performance (sensitivity 93.8%, specificity 94.6%, AUROC 98.7%). Adding more clinical variables and features further improved the performance of the models slightly (XGBoost: sensitivity 94.1%, specificity of 94.6%, AUROC 98.8%).

CONCLUSIONS: Artificial intelligence models have potential to become valuable tools for predicting ICP insults in advance during neurointensive care. The fact that common off-the-shelf models, such as XGBoost, performed well in predicting ICP insults opens new possibilities that can lead to faster advances in the field and earlier clinical implementations.

来源:Neurocrit Care,查看原文。版权归原作者所有。

参考来源

  1. Galos P, Hult L, Zachariah D, et al. Machine Learning Based Prediction of Imminent ICP Insults During Neurocritical Care of Traumatic Brain Injury. Neurocrit Care. 2024. PMID: 39322847. doi:10.1007/s12028-024-02119-7

供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。