From the Department of Neurology (J.H., H.L., I.H.L., Y.D.K., H.S.N.) and Department of Internal Medicine (J.-S.K.), Division of Cardiology, Yonsei University College of Medicine, Seoul; Department of Neurology (J.Y.), Yonsei University College of Medicine, Yongin Severance Hospital; and Integrative Research Center for Cerebrovascular and Cardiovascular Diseases (E.P.), Seoul, Korea.
Neurology. 2022 Jul 5;99(1):e55-e65. doi: 10.1212/WNL.0000000000200576. Epub 2022 Apr 25.
A machine learning technique for identifying hidden coronary artery disease (CAD) might be useful. We developed and validated machine learning models to predict patients with hidden CAD and to assess long-term outcomes in patients with acute ischemic stroke.
Multidetector coronary CT was performed for patients without a known history of CAD. Primary outcomes were defined as having any degree of CAD and having obstructive CAD (≥50% stenosis). Demographic variables, risk factors, laboratory results, Trial of ORG 10172 in Acute Stroke Treatment classification, NIH Stroke Scale score, blood pressure, and carotid artery stenosis were used to develop and validate machine learning models to predict CAD. Area under the receiver operating characteristic curves (AUC) was calculated for performance analysis, and Kaplan-Meier and Cox survival analyses of long-term outcomes were performed. Major adverse cardiovascular events (MACEs) were defined as ischemic stroke, myocardial infarction, unstable angina, urgent coronary revascularization, and cardiovascular mortality.
Overall, 1,710 patients were included for the training dataset and 348 patients for the validation dataset. An extreme gradient boosting model was developed to predict any degree of CAD, which showed an AUC of 0.763 (95% CI 0.711-0.814) on validation. A logistic regression model was used to predict obstructive CAD and had an AUC of 0.714 (95% CI 0.692-0.799). During the first 5 years of follow-up, MACEs occurred more frequently with predictions of any CAD ( = 0.022) or obstructive CAD ( < 0.001). Cox proportional analysis showed that the hazard ratio of MACE was 1.5 (95% CI 1.1-2.2; = 0.016) with prediction of any CAD, whereas it was 1.9 (95% CI 1.3-2.6; < 0.001) for obstructive CAD.
We demonstrated that machine learning may help identify hidden CAD in patients with acute ischemic stroke. Long-term outcomes were also associated with prediction results.
This study provides Class II evidence that in patients with acute ischemic stroke with CAD risk factors but no known history of CAD, a machine learning model predicts CAD on multidetector coronary CT with an AUC of 0.763 (95% CI 0.711-0.814).
一种用于识别隐匿性冠状动脉疾病（CAD）的机器学习技术可能会很有用。我们开发并验证了机器学习模型，以预测隐匿性 CAD 患者，并评估急性缺血性脑卒中患者的长期预后。
对无已知 CAD 病史的患者进行多排螺旋 CT 冠状动脉成像检查。主要结局定义为存在任何程度的 CAD 和存在阻塞性 CAD（≥50%狭窄）。使用人口统计学变量、危险因素、实验室结果、急性脑卒中治疗试验分类、国立卫生研究院脑卒中量表评分、血压和颈动脉狭窄，来开发和验证机器学习模型以预测 CAD。计算受试者工作特征曲线下面积（AUC）以进行性能分析，并进行 Kaplan-Meier 和 Cox 生存分析以评估长期预后。主要不良心血管事件（MACEs）定义为缺血性脑卒中、心肌梗死、不稳定型心绞痛、紧急冠状动脉血运重建和心血管死亡。
共纳入 1710 例患者进行训练数据集分析，348 例患者进行验证数据集分析。采用极端梯度提升模型预测任何程度的 CAD，验证集 AUC 为 0.763（95%CI 0.711-0.814）。采用逻辑回归模型预测阻塞性 CAD，AUC 为 0.714（95%CI 0.692-0.799）。在随访的前 5 年中，CAD 预测阳性（=0.022）或阻塞性 CAD 预测阳性（<0.001）的患者更常发生 MACEs。Cox 比例风险分析显示，CAD 预测阳性的 MACE 风险比为 1.5（95%CI 1.1-2.2；=0.016），而阻塞性 CAD 预测阳性的风险比为 1.9（95%CI 1.3-2.6；<0.001）。
我们证明机器学习可能有助于识别急性缺血性脑卒中患者中的隐匿性 CAD。长期预后也与预测结果相关。
本研究提供了 II 级证据，在伴有 CAD 危险因素但无已知 CAD 病史的急性缺血性脑卒中患者中，多排螺旋 CT 冠状动脉成像检查的机器学习模型预测 CAD 的 AUC 为 0.763（95%CI 0.711-0.814）。
