Bustamante Alejandro, Giralt Dolors, García-Berrocoso Teresa, Rubiera Marta, Álvarez-Sabín José, Molina Carlos, Serena Joaquín, Montaner Joan
Neurovascular Research Laboratory, Institut de Recerca, Hospital Universitari Vall d'Hebron-Universitat Autónoma de Barcelona, Spain.
Stroke Unit, Department of Neurology, Hospital Universitari Vall d'Hebron, Spain.
Eur Stroke J. 2017 Mar;2(1):54-63. doi: 10.1177/2396987316681872. Epub 2016 Nov 28.
Controversies remain on whether post-stroke complications represent an independent predictor of poor outcome or just a reflection of stroke severity. We aimed to identify which post-stroke complications have the highest impact on in-hospital mortality by using machine learning techniques. Secondary aim was identification of patient's subgroups in which complications have the highest impact.
Registro Nacional de Ictus de la Sociedad Española de Neurología is a stroke registry from 42 centers from the Spanish Neurological Society. Data from ischemic stroke patients were used to build a random forest by combining 500 classification and regression trees, to weight up the impact of baseline characteristics and post-stroke complications on in-hospital mortality. With the selected variables, a logistic regression analysis was performed to test for interactions.
12,227 ischemic stroke patients were included. In-hospital mortality was 5.9% and median hospital stay was 7(4-10) days. Stroke severity [National Institutes of Health Stroke Scale > 10, OR = 5.54(4.55-6.99)], brain edema [OR = 18.93(14.65-24.46)], respiratory infections [OR = 3.67(3.02-4.45)] and age [OR = 2.50(2.07-3.03) for >77 years] had the highest impact on in-hospital mortality in random forest, being independently associated with in-hospital mortality. Complications have higher odds ratios in patients with baseline National Institutes of Health Stroke Scale <10.
Our study identified brain edema and respiratory infections as independent predictors of in-hospital mortality, rather than just markers of more severe strokes. Moreover, its impact was higher in less severe strokes, despite lower frequency.
Brain edema and respiratory infections were the complications with a greater impact on in-hospital mortality, with the highest impact in patients with mild strokes. Further efforts on the prediction of these complications could improve stroke outcome.
关于中风后并发症是代表不良预后的独立预测因素还是仅仅反映中风严重程度，仍存在争议。我们旨在通过使用机器学习技术确定哪些中风后并发症对住院死亡率影响最大。次要目标是识别并发症影响最大的患者亚组。
西班牙神经学会国家卒中登记处是来自西班牙神经学会42个中心的卒中登记处。缺血性中风患者的数据用于通过组合500个分类和回归树构建随机森林，以权衡基线特征和中风后并发症对住院死亡率的影响。使用选定变量进行逻辑回归分析以检验相互作用。
纳入12227例缺血性中风患者。住院死亡率为5.9%，中位住院时间为7（4 - 10）天。中风严重程度[美国国立卫生研究院卒中量表>10，比值比（OR）=5.54（4.55 - 6.99）]、脑水肿[OR = 18.93（14.65 - 24.46）]、呼吸道感染[OR = 3.67（3.02 - 4.45）]和年龄[>77岁时OR = 2.50（2.07 - 3.03）]在随机森林中对住院死亡率影响最大，与住院死亡率独立相关。在基线美国国立卫生研究院卒中量表<10的患者中，并发症的比值比更高。
我们的研究确定脑水肿和呼吸道感染是住院死亡率的独立预测因素，而不仅仅是更严重中风的标志物。此外，尽管其发生率较低，但在不太严重的中风中其影响更大。
脑水肿和呼吸道感染是对住院死亡率影响更大的并发症，在轻度中风患者中影响最大。对这些并发症的预测进行进一步努力可能会改善中风预后。
