Cirillo Chiara, Matarrese Margherita A G, Monda Emanuele, Pagnano Maria Elisabetta, Vitale Jacopo, Verrillo Federica, Palmiero Giuseppe, Bassolino Sabrina, Buono Pietro, Caiazza Martina, Loffredo Francesco, Pecchia Leandro, Limongelli Giuseppe
Inherited and Rare Cardiovascular Diseases Unit, Department of Translational Medical Sciences, University of Campania "Luigi Vanvitelli", Naples, Italy.
Research Unit of Intelligent Health Technology for Health and Wellbeing, Department of Engineering, Università Campus Bio-Medico di Roma, Rome, Italy.
Int J Cardiol. 2025 Mar 1;422:132979. doi: 10.1016/j.ijcard.2025.132979. Epub 2025 Jan 10.
Left ventricular hypertrophy (LVH) is a common clinical finding associated with adverse cardiovascular outcomes. Once LVH is diagnosed, defining its cause has crucial clinical implications. Artificial intelligence (AI) may allow significant progress in the automated detection of LVH and its underlying causes from cardiovascular imaging. This systematic review aims to investigate the diagnostic performance of AI models developed to diagnose LVH and its common aetiologies.
MEDLINE/PubMed, EMBASE and Cochrane databases were systematically searched to identify relevant studies on echocardiography, cardiac magnetic resonance (CMR), and cardiac computed tomography (CT).
Thirty studies were included in this review. Of them, 14 were on echocardiography, 15 on CMR, and one on cardiac CT. Regarding the AI methods applied, 79 % of studies in echocardiography utilized deep learning (DL), 64 % employed convolutional neural networks (CNNs), and 21 % applied traditional machine learning (ML) algorithms. For CMR studies, 53 % used DL, 27 % relied on CNNs, and 47 % adopted traditional ML methods. All studies showed good diagnostic performances, but those applying AI tools to determine the underlying causes of LVH demonstrated the highest accuracy metrics compared to those focused on detecting LVH itself.
AI models designed to detect and differentiate LVH on cardiac imaging are currently under development and are demonstrating promising results. Further studies focusing on real-life validation of these models, and cost-effectiveness analyses are needed.
左心室肥厚（LVH）是一种常见的临床发现，与不良心血管结局相关。一旦诊断出LVH，明确其病因具有至关重要的临床意义。人工智能（AI）可能会在从心血管成像中自动检测LVH及其潜在病因方面取得重大进展。本系统评价旨在研究为诊断LVH及其常见病因而开发的AI模型的诊断性能。
系统检索MEDLINE/PubMed、EMBASE和Cochrane数据库，以识别有关超声心动图、心脏磁共振成像（CMR）和心脏计算机断层扫描（CT）的相关研究。
本评价纳入了30项研究。其中，14项关于超声心动图，15项关于CMR，1项关于心脏CT。关于所应用的AI方法，超声心动图研究中有79%使用深度学习（DL），64%采用卷积神经网络（CNN），21%应用传统机器学习（ML）算法。对于CMR研究，53%使用DL，27%依赖CNN，47%采用传统ML方法。所有研究均显示出良好的诊断性能，但与专注于检测LVH本身的研究相比，那些应用AI工具来确定LVH潜在病因的研究表现出最高的准确性指标。
旨在在心脏成像上检测和区分LVH的AI模型目前正在开发中，并显示出有前景的结果。需要进一步开展专注于这些模型的现实生活验证以及成本效益分析的研究。
