Form the Department of Neurosurgery (H.N., I.O., M.O., S.M.), Kyoto University Graduate School of Medicine, Kyoto, Japan.
Medical Innovation Center (N.O.), Kyoto University Graduate School of Medicine, Kyoto, Japan.
Stroke. 2019 Sep;50(9):2379-2388. doi: 10.1161/STROKEAHA.119.025411. Epub 2019 Aug 14.
Background and Purpose- The clinical course of acute ischemic stroke with large vessel occlusion (LVO) is a multifactorial process with various prognostic factors. We aimed to model this process with machine learning and predict the long-term clinical outcome of LVO before endovascular treatment and to compare our method with previously developed pretreatment scoring methods. Methods- The derivation cohort included 387 LVO patients, and the external validation cohort included 115 LVO patients with anterior circulation who were treated with mechanical thrombectomy. The statistical model with logistic regression without regularization and machine learning algorithms, such as regularized logistic regression, linear support vector machine, and random forest, were used to predict good clinical outcome (modified Rankin Scale score of 0-2 at 90 days) with standard and multiple pretreatment clinical variables. Five previously reported pretreatment scoring methods (the Pittsburgh Response to Endovascular Therapy score, the Stroke Prognostication Using Age and National Institutes of Health Stroke Scale index, the Totaled Health Risks in Vascular Events score, the Houston Intra-Arterial Therapy score, and the Houston Intra-Arterial Therapy 2 score) were compared with these models for the area under the receiver operating characteristic curve. Results- The area under the receiver operating characteristic curve of random forest, which was the worst among the machine learning algorithms, was significantly higher than those of the standard statistical model and the best model among the previously reported pretreatment scoring methods in the derivation (the area under the receiver operating characteristic curve were 0.85±0.07 for random forest, 0.78±0.08 for logistic regression without regularization, and 0.77±0.09 for Stroke Prognostication using Age and National Institutes of Health Stroke Scale) and validation cohorts (the area under the receiver operating characteristic curve were 0.87±0.01 for random forest, 0.56±0.07 for logistic regression without regularization, and 0.83±0.00 for Pittsburgh Response to Endovascular Therapy). Conclusions- Machine learning methods with multiple pretreatment clinical variables can predict clinical outcomes of patients with anterior circulation LVO who undergo mechanical thrombectomy more accurately than previously developed pretreatment scoring methods.
背景与目的-急性缺血性脑卒中伴大血管闭塞（LVO）的临床病程是一个多因素过程，存在多种预后因素。我们旨在通过机器学习对这一过程进行建模，并预测血管内治疗前 LVO 的长期临床结局，同时将我们的方法与先前开发的预处理评分方法进行比较。方法-推导队列纳入了 387 例 LVO 患者，外部验证队列纳入了 115 例接受机械取栓治疗的前循环 LVO 患者。使用无正则化逻辑回归的统计模型和机器学习算法，如正则化逻辑回归、线性支持向量机和随机森林，对标准和多个预处理临床变量进行预测，以评估 90 天时改良 Rankin 量表评分（0-2 分）的良好临床结局。将五种先前报道的预处理评分方法（匹兹堡血管内治疗反应评分、年龄和国立卫生研究院卒中量表指数用于卒中预后评分、血管事件总健康风险评分、休斯顿动脉内治疗评分和休斯顿动脉内治疗 2 评分）与这些模型的受试者工作特征曲线下面积进行比较。结果-随机森林的受试者工作特征曲线下面积（机器学习算法中最差的）在推导队列（随机森林为 0.85±0.07，无正则化逻辑回归为 0.78±0.08，年龄和国立卫生研究院卒中量表指数用于卒中预后评分 0.77±0.09）和验证队列（随机森林为 0.87±0.01，无正则化逻辑回归为 0.56±0.07，匹兹堡血管内治疗反应评分 0.83±0.00）中显著高于标准统计模型和最佳的先前报道的预处理评分方法。结论-与先前开发的预处理评分方法相比，使用多个预处理临床变量的机器学习方法可以更准确地预测接受机械取栓治疗的前循环 LVO 患者的临床结局。
