医学
危险分层
经皮冠状动脉介入治疗
心脏病学
内科学
经皮
拉伤
分层(种子)
残余物
剩余风险
冠状动脉造影
风险评估
风险因素
外科
血流动力学
放射科
介入心脏病学
梅德林
冠心病
作者
Jiayue Huang,Shengxian Tu,Haocheng Huang,Simone Fezzi,Jiaxin Zhong,Andreas Baumbach,Zhiqing Wang,Helen Parise,Chunming Li,Lianglong Chen,Charles Michael Gibson,Alexandra J. Lansky,William Wijns,on behalf of the SMART-CHOICE three investigators
出处
期刊:Eurointervention
[European Association of Percutaneous Cardiovascular Interventions]
日期:2026-09-01
卷期号:22 (18): e978-e989
标识
DOI:10.4244/eij-d-26-00126
摘要
BACKGROUND: Percutaneous coronary intervention effectively treats flow-limiting stenoses; however, untreated non-target vessels with vulnerable plaques remain a major contributor to future adverse cardiovascular events. Plaque strain is a promising marker of plaque vulnerability but traditionally requires complex modelling and expensive intracoronary imaging. We developed a novel artificial intelligence algorithm for subpixel-level lumen delineation, enabling real-time automated assessment of radial wall strain (RWS) from routine angiography. AIMS: This post hoc study sought to determine the prognostic value of RWS for predicting future cardiac events in non-target vessels over 5 years, using the high-quality TARGET All Comers randomised trial. METHODS: ) ≥13% was used to define increased plaque vulnerability. The primary endpoint was a non-target vessel-oriented composite endpoint (NT-VOCE), a composite of cardiac death, non-target vessel myocardial infarction and non-target vessel revascularisation over 5 years, as prospectively adjudicated in the parent trial. Following blinded RWS analysis, the results were integrated into the trial database, and the outcomes were unblinded and linked to corresponding vessel-level outcomes. RESULTS: independently predicted the NT-VOCE, with an adjusted hazard ratio (HR) of 4.82 (95% confidence interval [CI]: 3.14-7.40; p<0.0001) and an adjusted area under the curve (AUC) of 0.73 (95% CI: 0.69-0.78; p<0.0001). Predictive accuracy was highest for non-target vessel revascularisation (adjusted AUC 0.92, 95% CI: 0.88-0.95; p<0.0001). In the subgroup with high-quality angiographic images, RWS demonstrated even greater predictive performance for the NT-VOCE (adjusted HR 6.89, 95% CI: 3.15-15.07; p<0.0001). CONCLUSIONS: was strongly associated with the NT-VOCE, with the highest predictive accuracy in vessels with high-quality angiographic imaging. Ongoing and planned prospective, randomised trials are evaluating the role of RWS-guided risk stratification.
科研通智能强力驱动
Strongly Powered by AbleSci AI