Lin Guisen, Liu Qile, Chen Yuchen, Zong Xiaodan, Xi Yue, Li Tingyu, Yang Yuelong, Zeng An, Chen Minglei, Liu Chen, Liang Yanting, Xu Xiaowei, Huang Meiping
Department of Radiology, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China.
Department of Radiology, Shenzhen Children's Hospital, Shenzhen, China.
Front Cardiovasc Med. 2021 Nov 25;8:771504. doi: 10.3389/fcvm.2021.771504. eCollection 2021.
Patients with ischemic stroke (IS), transient ischemic attack (TIA), and/or peripheral artery disease (PAD) represent a population with an increased risk of coronary artery disease. Prognostic risk assessment to identify those with the highest risk that may benefit from more intensified treatment remains challenging. To explore the feasibility and capability of machine learning (ML) to predict long-term adverse cardiac-related prognosis in patients with IS, TIA, and/or PAD. We analyzed 636 consecutive patients with a history of IS, TIA, and/or PAD. All patients underwent a coronary CT angiography (CCTA) scan. Thirty-five clinical data and 34 CCTA metrics underwent automated feature selection for ML model boosting. The clinical outcome included all-cause mortality (ACM) and major adverse cardiac events (MACE) (ACM, unstable angina requiring hospitalization, non-fatal myocardial infarction (MI), and revascularization 90 days after the index CCTA). During the follow-up of 3.9 ± 1.6 years, 21 patients had unstable angina requiring hospitalization, eight had a MI, 23 had revascularization and 13 deaths. ML demonstrated a significant higher area-under-curve compared with the modified Duke index (MDI), segment stenosis score (SSS), segment involvement score (SIS), and Framingham risk score (FRS) for the prediction of ACM (ML:0.92 vs. MDI:0.66, SSS:0.68, SIS:0.67, FRS:0.51, all < 0.001) and MACE (ML:0.84 vs. MDI:0.82, SSS:0.76, SIS:0.73, FRS:0.53, all < 0.05). Among the patients with IS, TIA, and/or PAD, ML demonstrated a better capability of predicting ACM and MCAE than clinical scores and CCTA metrics.
患有缺血性中风（IS）、短暂性脑缺血发作（TIA）和/或外周动脉疾病（PAD）的患者是冠状动脉疾病风险增加的人群。进行预后风险评估以识别那些可能从更强化治疗中获益的高风险患者仍然具有挑战性。为了探索机器学习（ML）预测IS、TIA和/或PAD患者长期不良心脏相关预后的可行性和能力。我们分析了636例连续的有IS、TIA和/或PAD病史的患者。所有患者均接受了冠状动脉CT血管造影（CCTA）扫描。对35项临床数据和34项CCTA指标进行自动特征选择，以增强ML模型。临床结局包括全因死亡率（ACM）和主要不良心脏事件（MACE）（ACM、需要住院治疗的不稳定型心绞痛、非致命性心肌梗死（MI）以及索引CCTA后90天的血运重建）。在3.9±1.6年的随访期间，21例患者发生需要住院治疗的不稳定型心绞痛，8例发生MI，23例进行了血运重建，13例死亡。在预测ACM方面，ML显示出比改良杜克指数（MDI）、节段狭窄评分（SSS）、节段累及评分（SIS）和弗雷明汉风险评分（FRS）显著更高的曲线下面积（ML：0.92 vs. MDI：0.66、SSS：0.68、SIS：0.67、FRS：0.51，均P<0.001），在预测MACE方面也是如此（ML：0.84 vs. MDI：0.82、SSS：0.76、SIS：0.73、FRS：0.53，均P<0.05）。在患有IS、TIA和/或PAD的患者中，ML在预测ACM和MACE方面比临床评分和CCTA指标表现出更好的能力。
