Lazaridis Christos, Ajith Aswathy, Mansour Ali, Okonkwo David O, Diaz-Arrastia Ramon, Mayampurath Anoop
Departments of Neurology and Neurosurgery, University of Chicago Medical Center, University of Chicago, Chicago, Illinois, USA.
Department of Computer Science, University of Chicago, Chicago, Illinois, USA.
Neurotrauma Rep. 2022 Oct 27;3(1):473-478. doi: 10.1089/neur.2022.0055. eCollection 2022.
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 (PbtO) data obtained from the BOOST-II trial with the goal of constructing robust quantitative models to predict ICP/PbtO 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 PbtO 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 PbtO, 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 PbtO 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.
目前针对颅内高压和脑组织缺氧的处理方法是基于固定阈值的被动反应式方法。我们对从BOOST-II试验中获得的高频颅内压（ICP）和部分脑组织氧分压（PbtO）数据使用了统计机器学习方法，目的是构建强大的定量模型来预测ICP/PbtO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。我们将数据集按70-30%的比例划分为训练集和测试集，并对所有模型采用离散时间生存分析框架和5折超参数优化策略。我们通过接受者操作特征（AUROC）曲线下的面积来比较模型在区分ICP升高或PbtO降低的事件与非事件方面的性能。我们通过决策曲线分析（DCA）进一步分析了临床实用性。在考虑区分能力、特征数量和可解释性时，我们确定结合最近的ICP读数、发作次数以及前30分钟内的纵向趋势的随机森林模型在预测未来30分钟内的ICP危机事件方面表现最佳（AUC为0.78）。对于PbtO，利用最近读数、发作次数以及前30分钟内纵向趋势的逻辑回归模型表现最佳（AUC为0.84）。决策曲线分析表明，对于ICP和PbtO预测的广泛风险阈值具有临床实用性。根据对特定患者针对警报做出的给定干预的获益-风险比的评估，可接受的警报阈值范围可以从20%到80%。
