Klein-Murrey Lauren, Tirschwell David L, Hippe Daniel S, Kharaji Mona, Sanchez-Vizcaino Cristina, Haines Brooke, Balu Niranjan, Hatsukami Thomas S, Yuan Chun, Akoum Nazem W, Lila Eardi, Mossa-Basha Mahmud
Department of Neurology, Harborview Medical Center, University of Washington School of Medicine, 325 Ninth Avenue, Seattle, WA, USA.
Clinical Research Division, Fred Hutchinson Cancer Center, Seattle, WA, USA.
J Neurol. 2024 Dec 21;272(1):87. doi: 10.1007/s00415-024-12848-6.
Embolic stroke of unidentified source (ESUS) represents 10-25% of all ischemic strokes. Our goal was to determine whether ESUS could be reclassified to cardioembolic (CE) or large-artery atherosclerosis (LAA) with machine learning (ML) using conventional clinical data.
We retrospectively collected conventional clinical features, including patient, imaging (MRI, CT/CTA), cardiac, and serum data from established cases of CE and LAA stroke, and factors with p < 0.2 in univariable analysis were used for creating a ML predictive tool. We then applied this tool to ESUS cases, with ≥ 75% likelihood serving as the threshold for reclassification to CE or LAA. In patients with longitudinal data, we evaluated future cardiovascular events.
191 ischemic stroke patients (80 CE, 61 LAA, 50 ESUS) were included. Seven and 6 predictors positively associated with CE and LAA etiology, respectively. The c-statistic for discrimination between CE and LAA was 0.88. The strongest predictors for CE were left atrial volume index (OR = 2.17 per 1 SD increase) and BNP (OR = 1.83 per 1 SD increase), while the number of non-calcified stenoses ≥ 30% upstream (OR = 0.34 per 1 SD increase) and not upstream (OR = 0.74 per 1 SD increase) from the infarct were for LAA. When applied to ESUS cases, the model reclassified 40% (20/50), with 11/50 reclassified to CE and 9/50 reclassified to LAA. In 21/50 ESUS with 30-day cardiac monitoring, 1/4 in CE and 3/16 equivocal reclassifications registered cardiac events, while 0/1 LAA reclassifications showed events.
ML tools built using standard ischemic stroke workup clinical biomarkers can potentially reclassify ESUS stroke patients into cardioembolic or atherosclerotic etiology categories.
不明来源栓塞性卒中（ESUS）占所有缺血性卒中的10%-25%。我们的目标是确定能否使用机器学习（ML）并借助传统临床数据将ESUS重新分类为心源性栓塞（CE）或大动脉粥样硬化（LAA）。
我们回顾性收集了CE和LAA卒中确诊病例的传统临床特征，包括患者、影像学（MRI、CT/CTA）、心脏及血清数据，并将单变量分析中p<0.2的因素用于创建ML预测工具。然后我们将此工具应用于ESUS病例，将≥75%的可能性作为重新分类为CE或LAA的阈值。对于有纵向数据的患者，我们评估了未来的心血管事件。
纳入了191例缺血性卒中患者（80例CE、61例LAA、50例ESUS）。分别有7个和6个预测因素与CE和LAA病因呈正相关。CE和LAA之间鉴别诊断的c统计量为0.88。CE最强的预测因素是左心房容积指数（每增加1个标准差，OR=2.17）和脑钠肽（每增加1个标准差，OR=1.83），而梗死灶上游非钙化狭窄≥30%的数量（每增加1个标准差，OR=0.34）以及梗死灶非上游的数量（每增加1个标准差，OR=0.74）与LAA相关。当应用于ESUS病例时，该模型重新分类了40%（20/50），其中11/50重新分类为CE，9/50重新分类为LAA。在50例接受30天心脏监测的ESUS患者中，CE重新分类的4例中有1例、不确定重新分类的16例中有3例记录到心脏事件，而LAA重新分类的1例中无事件发生。
使用标准缺血性卒中检查临床生物标志物构建的ML工具可能会将ESUS卒中患者重新分类为心源性栓塞或动脉粥样硬化病因类别。
