Biswas Dhruva, Aminorroaya Arya, Croon Philip M, Batinica Bruno, Pedroso Aline F, Khera Rohan
Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA.
Cardiovascular Data Science (CarDS) Lab, Yale School of Medicine, 195 Church Street, 6th Floor, New Haven, CT, 06510, USA.
Curr Atheroscler Rep. 2025 Sep 1;27(1):86. doi: 10.1007/s11883-025-01337-4.
To define the emerging role of artificial intelligence-enhanced electrocardiography (AI-ECG) in advancing population-level screening for atherosclerotic cardiovascular disease (ASCVD), we provide a comprehensive overview of its role in predicting major adverse cardiovascular events and detecting subclinical coronary artery disease. We also outline the clinical, methodological, and implementation challenges that must be addressed for widespread adoption.
State-of-the-art AI-ECG models exhibit high accuracy, correctly re-classifying patients deemed 'low risk' by traditional risk models. They also compress the prediction horizon from a decade to just a few years, suggesting opportunities for early detection and more personalized intervention. However, validation remains largely retrospective and hospital-based, with referral and ascertainment biases limiting generalizability. There is no evidence thus far for an externally validated AI-ECG model that can either define or improve the detection of ASCVD outcomes independent of standard risk factors. AI-enhanced ECG interpretation has the potential to transform a universal, inexpensive test into a powerful screening and prognostication tool for ASCVD. Realizing this potential will require prospective studies to confirm that AI-ECG-guided ASCVD screening improves patient outcomes across diverse populations. Earning trust among physicians and patients will require addressing key logistical challenges, including robust data governance, seamless workflow integration, and ongoing performance monitoring. Technological innovation, such as algorithms for single-lead ECGs on wearable and portable devices, could help enable the scalability needed for global impact on cardiovascular health.
为了明确人工智能增强心电图（AI-ECG）在推进动脉粥样硬化性心血管疾病（ASCVD）人群水平筛查中的新作用，我们全面概述了其在预测主要不良心血管事件和检测亚临床冠状动脉疾病方面的作用。我们还概述了广泛应用必须解决的临床、方法学和实施方面的挑战。
最先进的AI-ECG模型表现出高准确性，能够正确地对传统风险模型判定为“低风险”的患者进行重新分类。它们还将预测时间范围从十年压缩到短短几年，这为早期检测和更个性化的干预提供了机会。然而，验证在很大程度上仍然是回顾性的且基于医院，转诊和确诊偏倚限制了其普遍性。目前尚无证据表明存在一种经过外部验证的AI-ECG模型，能够独立于标准风险因素来定义或改善ASCVD结局的检测。人工智能增强的心电图解读有潜力将一种通用、廉价的检测转变为一种强大的ASCVD筛查和预后工具。要实现这一潜力，需要进行前瞻性研究，以确认AI-ECG指导的ASCVD筛查能改善不同人群的患者结局。要赢得医生和患者的信任，需要解决关键的后勤挑战，包括强大的数据治理、无缝的工作流程整合以及持续的性能监测。技术创新，如可穿戴和便携式设备上单导联心电图的算法，有助于实现对心血管健康产生全球影响所需的可扩展性。
