Roederer Alexander, Holmes John H, Smith Michelle J, Lee Insup, Park Soojin
Department of Computer and Information Science, School of Engineering and Applied Science, University of Pennsylvania, Philadelphia, PA, USA.
Neurocrit Care. 2014 Dec;21(3):444-50. doi: 10.1007/s12028-014-9976-9.
When vasospasm is detected after aneurysmal subarachnoid hemorrhage (aSAH), it is treated with hypertensive or endovascular therapy. Current classification methods are resource-intensive, relying on specialty-trained professionals (nursing exams, transcranial dopplers, and perfusion imaging). More passively obtained variables such as cerebrospinal fluid drainage volumes, sodium, glucose, blood pressure, intracranial pressure, and heart rate, have not been used to predict vasospasm. We hypothesize that these features may yield as much information as resource-intensive features to classify vasospasm.
We studied data from 81 aSAH patients presenting within two days of onset. Vasospasm class (VSP) was defined by angiographic vasospasm warranting endovascular treatment. Naïve Bayes (NB) and logistic regression (LR) classifiers were trained on selected variable feature sets from the first three days of illness. Performance of trained classifiers was evaluated using area under the receiver operator characteristic curve (AUC classifier) and F-measure (F classifier). Ablation analysis determined incremental utility of each variable and subsets.
43.2 % developed VSP. During feature selection, the only passively collected variable that did not yield a statistically significant summary statistic was CSF drainage volume. NB classifier trained on all passively obtained features (AUC NB 0.708 and F NB 0.636) outperformed NB classifier trained on resource-intensive features (AUC NB 0.501 and F NB 0.349).
Data-driven analysis of passively obtained clinical data predicted VSP better than current targeted resource-intensive monitoring techniques after aSAH. Automated classification of VSP may be possible.
在动脉瘤性蛛网膜下腔出血（aSAH）后检测到血管痉挛时，采用高血压治疗或血管内治疗。目前的分类方法资源消耗大，依赖专业培训的专业人员（护理检查、经颅多普勒检查和灌注成像）。脑脊液引流量、钠、葡萄糖、血压、颅内压和心率等更多被动获取的变量尚未用于预测血管痉挛。我们假设这些特征可能产生与资源密集型特征一样多的信息来对血管痉挛进行分类。
我们研究了81例发病两天内就诊的aSAH患者的数据。血管痉挛分级（VSP）由需要血管内治疗的血管造影血管痉挛定义。朴素贝叶斯（NB）和逻辑回归（LR）分类器在发病头三天的选定变量特征集上进行训练。使用受试者操作特征曲线下面积（AUC分类器）和F值（F分类器）评估训练后分类器的性能。消融分析确定每个变量和子集的增量效用。
43.2%的患者发生VSP。在特征选择过程中，唯一未产生具有统计学意义的汇总统计量的被动收集变量是脑脊液引流量。在所有被动获取的特征上训练的NB分类器（AUC NB 0.708和F NB 0.636）优于在资源密集型特征上训练的NB分类器（AUC NB 0.501和F NB 0.349）。
对被动获取临床数据进行数据驱动分析，比aSAH后当前针对性的资源密集型监测技术能更好地预测VSP。VSP的自动分类可能是可行的。
