当前位置: X-MOL 学术Stroke › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Stroke Prognostic Scores and Data-Driven Prediction of Clinical Outcomes After Acute Ischemic Stroke.
Stroke ( IF 8.3 ) Pub Date : 2020-03-25 , DOI: 10.1161/strokeaha.119.027300
Koutarou Matsumoto 1, 2 , Yasunobu Nohara 3 , Hidehisa Soejima 4 , Toshiro Yonehara 5 , Naoki Nakashima 3 , Masahiro Kamouchi 1, 6
Affiliation  

Background and Purpose- Several stroke prognostic scores have been developed to predict clinical outcomes after stroke. This study aimed to develop and validate novel data-driven predictive models for clinical outcomes by referring to previous prognostic scores in patients with acute ischemic stroke in a real-world setting. Methods- We used retrospective data of 4237 patients with acute ischemic stroke who were hospitalized in a single stroke center in Japan between January 2012 and August 2017. We first validated point-based stroke prognostic scores (preadmission comorbidities, level of consciousness, age, and neurological deficit [PLAN] score, ischemic stroke predictive risk score [IScore], and acute stroke registry and analysis of Lausanne [ASTRAL] score in all patients; Houston intraarterial recanalization therapy [HIAT] score, totaled health risks in vascular events [THRIVE] score, and stroke prognostication using age and National Institutes of Health Stroke Scale-100 [SPAN-100] in patients who received reperfusion therapy) in our cohort. We then developed predictive models using all available data by linear regression or decision tree ensembles (random forest and gradient boosting decision tree) and evaluated their area under the receiver operating characteristic curve for clinical outcomes after repeated random splits. Results- The mean (SD) age of the patients was 74.7 (12.9) years and 58.3% were men. Area under the receiver operating characteristic curves (95% CIs) of prognostic scores in our cohort were 0.92 PLAN score (0.90-0.93), 0.86 for IScore (0.85-0.87), 0.85 for ASTRAL score (0.83-0.86), 0.69 for HIAT score (0.62-0.75), 0.70 for THRIVE score (0.64-0.76), and 0.70 for SPAN-100 (0.63-0.76) for poor functional outcomes, and 0.87 for PLAN score (0.85-0.90), 0.88 for IScore (0.86-0.91), and 0.88 ASTRAL score (0.85-0.91) for in-hospital mortality. Internal validation of data-driven prediction models showed that their area under the receiver operating characteristic curves ranged between 0.88 and 0.94 for poor functional outcomes and between 0.84 and 0.88 for in-hospital mortality. Ensemble models of a decision tree tended to outperform linear regression models in predicting poor functional outcomes but not in predicting in-hospital mortality. Conclusions- Stroke prognostic scores perform well in predicting clinical outcomes after stroke. Data-driven models may be an alternative tool for predicting poststroke clinical outcomes in a real-world setting.

中文翻译:

急性缺血性中风后中风的预后评分和临床结果的数据驱动预测。

背景和目的-已开发出几种中风预后评分来预测中风后的临床结局。这项研究的目的是通过参考现实世界中急性缺血性卒中患者的先前预后评分,开发和验证新型的数据驱动的临床预后预测模型。方法-我们采用回顾性数据,回顾了2012年1月至2017年8月在日本单一卒中中心住院的4237例急性缺血性卒中患者。我们首先验证了基于穴位的卒中预后评分(入院合并症,意识水平,年龄和所有患者的神经功能缺损[PLAN]评分,缺血性卒中预测风险评分[IScore]和急性卒中登记和洛桑分析[ASTRAL]评分;休斯敦动脉再通治疗[HIAT]评分,在我们的队列中,使用年龄和美国国立卫生研究院卒中量表100 [SPAN-100]对年龄,血管事件的总体健康风险[THRIVE]评分和卒中预后进行了评估。然后,我们通过线性回归或决策树集成(随机森林和梯度增强决策树)使用所有可用数据开发了预测模型,并在反复随机分割后评估了其在接收器工作特征曲线下的面积,以用于临床结果。结果-患者的平均(SD)年龄为74.7(12.9)岁,男性为58.3%。在我们的队列中,预后评分的受试者工作特征曲线下面积(95%CI)分别为PLAN评分(0.90-0.93),IScore(0.85-0.87)0.86,ASTRAL评分(0.83-0.86)0.85,HIAT 0.69得分(0.62-0.75),THRIVE得分(0.64-0.76)为0.70,SPAN-100(0.63-0.76)对于功能不良的患者为0.70,PLAN评分(0.85-0.90)为0.87,IScore(0.86-0.91)为0.88,ASTRAL评分(0.85-0.91)对于医院内死亡率。对数据驱动的预测模型的内部验证表明,对于功能较差的结果,其在接受者操作特征曲线下的面积在0.88至0.94之间,对于住院死亡率,其范围在0.84至0.88之间。决策树的集成模型在预测较差的功能结局方面胜过线性回归模型,但在预测医院内死亡率方面却胜过线性回归模型。结论:中风的预后评分在预测中风后的临床结局方面表现良好。数据驱动模型可能是在现实环境中预测卒中后临床结局的替代工具。功能不良的结果为76),PLAN得分(0.85-0.90)为0.87,IScore(0.86-0.91)为0.88,ASTRAL得分(0.85-0.91)为院内死亡率。对数据驱动的预测模型的内部验证表明,对于功能较差的结果,其在接受者操作特征曲线下的面积在0.88至0.94之间,对于住院死亡率,其范围在0.84至0.88之间。决策树的集成模型在预测较差的功能结局方面胜过线性回归模型,但在预测医院内死亡率方面却胜过线性回归模型。结论:中风的预后评分在预测中风后的临床结局方面表现良好。数据驱动模型可能是在现实环境中预测卒中后临床结局的替代工具。功能不良的结果为76),PLAN得分(0.85-0.90)为0.87,IScore(0.86-0.91)为0.88,ASTRAL得分(0.85-0.91)为院内死亡率。对数据驱动的预测模型的内部验证表明,对于功能较差的结果,其在接受者操作特征曲线下的面积在0.88至0.94之间,对于住院死亡率,其范围在0.84至0.88之间。决策树的集成模型在预测较差的功能结局方面胜过线性回归模型,但在预测医院内死亡率方面却胜过线性回归模型。结论:中风的预后评分在预测中风后的临床结局方面表现良好。数据驱动模型可能是在现实环境中预测卒中后临床结局的替代工具。院内死亡率为88 ASTRAL(0.85-0.91)。对数据驱动的预测模型的内部验证表明,对于功能较差的结果,其在接受者操作特征曲线下的面积在0.88至0.94之间,对于住院死亡率,其范围在0.84至0.88之间。决策树的集成模型在预测较差的功能结局方面胜过线性回归模型,但在预测医院内死亡率方面却胜过线性回归模型。结论:中风的预后评分在预测中风后的临床结局方面表现良好。数据驱动模型可能是在现实环境中预测卒中后临床结局的替代工具。院内死亡率为88 ASTRAL(0.85-0.91)。对数据驱动的预测模型的内部验证表明,对于功能较差的结果,其在接受者操作特征曲线下的面积在0.88至0.94之间,对于住院死亡率,其范围在0.84至0.88之间。决策树的集成模型在预测较差的功能结局方面胜过线性回归模型,但在预测医院内死亡率方面却胜过线性回归模型。结论:中风的预后评分在预测中风后的临床结局方面表现良好。数据驱动模型可能是在现实环境中预测卒中后临床结局的替代工具。对数据驱动的预测模型的内部验证表明,对于功能较差的结果,其在接受者操作特征曲线下的面积在0.88至0.94之间,对于住院死亡率,其范围在0.84至0.88之间。决策树的集成模型在预测较差的功能结局方面胜过线性回归模型,但在预测医院内死亡率方面却胜过线性回归模型。结论:中风的预后评分在预测中风后的临床结局方面表现良好。数据驱动模型可能是在现实环境中预测卒中后临床结局的替代工具。对数据驱动的预测模型的内部验证表明,对于功能较差的结果,其在接受者操作特征曲线下的面积在0.88至0.94之间,对于住院死亡率,其范围在0.84至0.88之间。决策树的集成模型在预测较差的功能结局方面胜过线性回归模型,但在预测医院内死亡率方面却胜过线性回归模型。结论:中风的预后评分在预测中风后的临床结局方面表现良好。数据驱动模型可能是在现实环境中预测卒中后临床结局的替代工具。决策树的集成模型在预测较差的功能结局方面胜过线性回归模型,但在预测医院内死亡率方面却胜过线性回归模型。结论:中风的预后评分在预测中风后的临床结局方面表现良好。数据驱动模型可能是在现实环境中预测卒中后临床结局的替代工具。决策树的集成模型在预测较差的功能结局方面胜过线性回归模型,但在预测医院内死亡率方面却胜过线性回归模型。结论:中风的预后评分在预测中风后的临床结局方面表现良好。数据驱动模型可能是在现实环境中预测卒中后临床结局的替代工具。
更新日期:2020-03-25
down
wechat
bug