Prediction of Intracranial Hypertension and Brain Tissue Hypoxia Utilizing High-Resolution Data from the BOOST-II Clinical Trial.
Prediction of Intracranial Hypertension and Brain Tissue Hypoxia Utilizing High-Resolution Data from the BOOST-II Clinical Trial.
复制标题
DOI：
10.1089/neur.2022.0055
复制
发表时间：
2022
影响因子：
2.4
通讯作者：
BOOST II Investigators, B. O. O. S. T. I. I. Investigators
中科院分区：
文献类型：
--
作者：
Lazaridis, Christos;Ajith, Aswathy;Mansour, Ali;Okonkwo, David O.;Diaz-Arrastia, Ramon;Mayampurath, Anoop;BOOST II Investigators, B. O. O. S. T. I. I. Investigators
目前的方法颅内高压和脑组织缺氧是反应性的，基于固定的阈值。我们对BOOST-II试验中获得的高频颅内压（ICP）和部分脑组织氧张力（PbtO2）数据使用统计机器学习，目的是构建可靠的定量模型来预测ICP/PbtO2危机。我们推导了以下机器学习模型：逻辑回归（LR）、弹性网络和随机森林。我们将数据集分成70-30%用于训练和测试，并对所有模型使用离散时间生存分析框架和5倍超参数优化策略。我们比较了模型对ICP升高或低PbtO2事件和非事件的区分性能与接受者工作特征（AUROC）曲线下面积的关系。我们进一步通过决策曲线分析（DCA）分析临床效用。当考虑到歧视、特征数量和可解释性时，我们确定了结合最近的ICP读数、集数和前30分钟的纵向趋势的RF模型，作为预测未来30分钟内ICP危机事件的最佳表现（AUC为0.78）。对于PbtO2，利用最近的阅读、剧集数和前30分钟的纵向趋势的LR模型表现最佳（AUC, 0.84）。DCA在ICP和PbtO2预测的广泛风险阈值方面显示出临床实用性。可接受的警报阈值可从20%到80%不等，这取决于针对警报的特定干预措施的效益-风险比评估。
The current approach to intracranial hypertension and brain tissue hypoxia is reactive, based on fixed thresholds. We used statistical machine learning on high-frequency intracranial pressure (ICP) and partial brain tissue oxygen tension (PbtO2) data obtained from the BOOST-II trial with the goal of constructing robust quantitative models to predict ICP/PbtO2 crises. We derived the following machine learning models: logistic regression (LR), elastic net, and random forest. We split the data set into 70–30% for training and testing and utilized a discrete-time survival analysis framework and 5-fold hyperparameter optimization strategy for all models. We compared model performances on discrimination between events and non-events of increased ICP or low PbtO2 with the area under the receiver operating characteristic (AUROC) curve. We further analyzed clinical utility through a decision curve analysis (DCA). When considering discrimination, the number of features, and interpretability, we identified the RF model that combined the most recent ICP reading, episode number, and longitudinal trends over the preceding 30 min as the best performing for predicting ICP crisis events within the next 30 min (AUC 0.78). For PbtO2, the LR model utilizing the most recent reading, episode number, and longitudinal trends over the preceding 30 min was the best performing (AUC, 0.84). The DCA showed clinical usefulness for wide risk of thresholds for both ICP and PbtO2 predictions. Acceptable alerting thresholds could range from 20% to 80% depending on a patient-specific assessment of the benefit-risk ratio of a given intervention in response to the alert.
登录
查看更多内容
影响因子：
3.6
作者：
Vickers, Andrew J.;Elkin, Elena B.
通讯作者：
Elkin, Elena B.
影响因子：
4.8
作者：
Carney, Nancy;Totten, Annette M.;Ghajar, Jamshid
通讯作者：
Ghajar, Jamshid
影响因子：
8.8
作者：
Hravnak, Marilyn;DeVita, Michael A.;Pinsky, Michael R.
通讯作者：
Pinsky, Michael R.
影响因子：
38.9
作者：
Chesnut, Randall;Aguilera, Sergio;Hawryluk, Gregory W. J.
通讯作者：
Hawryluk, Gregory W. J.
影响因子：
4.1
作者：
Lazaridis, Christos;DeSantis, Stacia M.;Czosnyka, Marek
通讯作者：
Czosnyka, Marek