文献速递脑血管病

心源性卒中的自动化电子表型识别

Automated Electronic Phenotyping of Cardioembolic Stroke.
PubMed 文献 · Stroke · 2020-12-10

本研究基于电子健康记录数据库,开发并验证了自动化算法识别心源性卒中的可行性。在Massachusetts General Hospital缺血性卒中登记(N=1598)中,随机森林模型识别心源性卒中的准确率达92.2%,AUC为91.1%(95%CI 87.5%-93.9%)。

要点

  • 基于电子健康记录的正则表达式算法提取心源性卒中特征,平均阳性预测值达95%。
  • 随机森林模型识别心源性卒中的准确率为92.2%,AUC为91.1%。
  • 房颤、年龄、扩张型心肌病、充血性心力衰竭、卵圆孔未闭、二尖瓣环钙化和近期心肌梗死是最具鉴别力的特征。

核心结论

  • 基于电子健康记录数据的机器学习方法识别心源性卒中是可行的。

研究设计与样本

  • 在Massachusetts General Hospital缺血性卒中登记(2002-2010年,N=1598)中,比较多种机器学习算法判别心源性卒中的性能,该登记具有既往裁定的TOAST和Causative Classification of Stroke亚型。

主要发现

  • 基于正则表达式的特征提取算法在11项超声心动图特征上平均阳性预测值为95%(范围88%-100%)。
  • 在1598例患者中,1068例在卒中事件附近预定义时间窗内具有任何心源性卒中特征。
  • 心源性卒中患者倾向于年龄更大、具有更多基于TOAST的合并症,且房颤比例为82.3%。
  • 最佳模型为随机森林,准确率92.2%,受试者工作特征曲线下面积为91.1%(95%CI 87.5%-93.9%)。
  • 最具鉴别力的特征包括房颤、年龄、扩张型心肌病、充血性心力衰竭、卵圆孔未闭、二尖瓣环钙化和近期心肌梗死。

关键数值与推荐

  • 正则表达式特征提取算法在11项超声心动图特征上的平均阳性预测值为95%(范围88%-100%)。
  • 随机森林模型识别心源性卒中的准确率为92.2%,AUC为91.1%(95%CI 87.5%-93.9%)。

临床怎么用

  • 可利用电子健康记录数据自动化识别心源性卒中,辅助风险分层和二级预防。
  • 房颤、年龄、扩张型心肌病、充血性心力衰竭、卵圆孔未闭、二尖瓣环钙化和近期心肌梗死是识别心源性卒中的关键特征。

局限性

  • 未来需要进一步工作以提高自动化心源性卒中识别的准确性。
  • 需要评估电子表型算法在不同临床环境中的泛化能力。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND AND PURPOSE: Oral anticoagulation is generally indicated for cardioembolic strokes, but not for other stroke causes. Consequently, subtype classification of ischemic stroke is important for risk stratification and secondary prevention. Because manual classification of ischemic stroke is time-intensive, we assessed the accuracy of automated algorithms for performing cardioembolic stroke subtyping using an electronic health record (EHR) database. METHODS: We adapted TOAST (Trial of ORG 10172 in Acute Stroke Treatment) features associated with cardioembolic stroke for derivation in the EHR. Using administrative codes and echocardiographic reports within Mass General Brigham Biobank (N=13 079), we iteratively developed EHR-based algorithms to define the TOAST cardioembolic stroke features, revising regular expression algorithms until achieving positive predictive value ≥80%. We compared several machine learning-based statistical algorithms for discriminating cardioembolic stroke using the feature algorithms applied to EHR data from 1598 patients with acute ischemic strokes from the Massachusetts General Hospital Ischemic Stroke Registry (2002-2010) with previously adjudicated TOAST and Causative Classification of Stroke subtypes. RESULTS: Regular expression-based feature extraction algorithms achieved a mean positive predictive value of 95% (range, 88%-100%) across 11 echocardiographic features. Among 1598 patients from the Massachusetts General Hospital Ischemic Stroke Registry, 1068 had any cardioembolic stroke feature within predefined time windows in proximity to the stroke event. Cardioembolic stroke tended to occur at an older age, with more TOAST-based comorbidities, and with atrial fibrillation (82.3%). The best model was a random forest with 92.2% accuracy and area under the receiver operating characteristic curve of 91.1% (95% CI, 87.5%-93.9%). Atrial fibrillation, age, dilated cardiomyopathy, congestive heart failure, patent foramen ovale, mitral annulus calcification, and recent myocardial infarction were the most discriminatory features. CONCLUSIONS: Machine learning-based identification of cardioembolic stroke using EHR data is feasible. Future work is needed to improve the accuracy of automated cardioembolic stroke identification and assess generalizability of electronic phenotyping algorithms across clinical settings.

来源:Stroke,查看原文。版权归原作者所有。

引用

  1. Guan W, Ko D, Khurshid S, et al. Automated Electronic Phenotyping of Cardioembolic Stroke. Stroke. 2020. PMID: 33297865. doi:10.1161/STROKEAHA.120.030663

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。