Moosavi Amirhossein, Huang Steven, Vahabi Maryam, Motamedivafa Bahar, Tian Nelly, Mahmood Rafid, Liu Peter, Sun Christopher L F
Telfer School of Management, University of Ottawa, Ottawa, Ontario, Canada.
University of Ottawa Heart Institute, University of Ottawa, Ottawa, Ontario, Canada.
JACC Adv. 2024 Aug 28;3(9):101202. doi: 10.1016/j.jacadv.2024.101202. eCollection 2024 Sep.
Despite the potential of artificial intelligence (AI) in enhancing cardiovascular care, its integration into clinical practice is limited by a lack of evidence on its effectiveness with respect to human experts or gold standard practices in real-world settings.
The purpose of this study was to identify AI interventions in cardiology that have been prospectively validated against human expert benchmarks or gold standard practices, assessing their effectiveness, and identifying future research areas.
We systematically reviewed Scopus and MEDLINE to identify peer-reviewed publications that involved prospective human validation of AI-based interventions in cardiology from January 2015 to December 2023.
Of 2,351 initial records, 64 studies were included. Among these studies, 59 (92.2%) were published after 2020. A total of 11 (17.2%) randomized controlled trials were published. AI interventions in 44 articles (68.75%) reported definite clinical or operational improvements over human experts. These interventions were mostly used in imaging (n = 14, 21.9%), ejection fraction (n = 10, 15.6%), arrhythmia (n = 9, 14.1%), and coronary artery disease (n = 12, 18.8%) application areas. Convolutional neural networks were the most common predictive model (n = 44, 69%), and images were the most used data type (n = 38, 54.3%). Only 22 (34.4%) studies made their models or data accessible.
This review identifies the potential of AI in cardiology, with models often performing equally well as human counterparts for specific and clearly scoped tasks suitable for such models. Nonetheless, the limited number of randomized controlled trials emphasizes the need for continued validation, especially in real-world settings that closely examine joint human AI decision-making.
尽管人工智能（AI）在改善心血管护理方面具有潜力，但其在临床实践中的应用受到限制，因为在现实环境中，缺乏关于其相对于人类专家或金标准实践有效性的证据。
本研究的目的是识别心脏病学领域中已针对人类专家基准或金标准实践进行前瞻性验证的人工智能干预措施，评估其有效性，并确定未来的研究领域。
我们系统地检索了Scopus和MEDLINE数据库，以确定2015年1月至2023年12月期间涉及对心脏病学中基于人工智能的干预措施进行前瞻性人体验证的同行评审出版物。
在2351条初始记录中，纳入了64项研究。其中，59项（92.2%）研究于2020年后发表。共发表了11项（17.2%）随机对照试验。44篇文章（68.75%）中的人工智能干预措施报告了相对于人类专家在临床或操作方面有明确改善。这些干预措施主要用于成像（n = 14，21.9%）、射血分数（n = 10，15.6%）、心律失常（n = 9，14.1%）和冠状动脉疾病（n = 12，18.8%）应用领域。卷积神经网络是最常见的预测模型（n = 44，69%），图像是最常用的数据类型（n = 38，54.3%）。只有22项（34.4%）研究提供了其模型或数据。
本综述确定了人工智能在心脏病学中的潜力，对于适合此类模型的特定且范围明确的任务，模型的表现通常与人类相当。尽管如此，随机对照试验数量有限，强调了持续验证的必要性，特别是在密切检查人机联合决策的现实环境中。
