Antoun Ibrahim, Nizam Ali, Ebeid Armia, Rajesh Mariya, Abdelrazik Ahmed, Eldesouky Mahmoud, Thu Kaung Myat, Barker Joseph, Layton Georgia R, Zakkar Mustafa, Ibrahim Mokhtar, Safwan Kassem, Dibek Radek M, Somani Riyaz, Ng G André, Bolger Aiden
Department of Cardiology, University Hospitals of Leicester NHS Trust, Glenfield Hospital, LE3 9QP Leicester, UK.
Department of Cardiovascular Sciences, Clinical Science Wing, University of Leicester, Glenfield Hospital, LE3 9QP Leicester, UK.
Rev Cardiovasc Med. 2025 Aug 28;26(8):41523. doi: 10.31083/RCM41523. eCollection 2025 Aug.
Adult congenital heart disease (ACHD) constitutes a heterogeneous and expanding patient cohort with distinctive diagnostic and management challenges. Conventional detection methods are ineffective at reflecting lesion heterogeneity and the variability in risk profiles. Artificial intelligence (AI), including machine learning (ML) and deep learning (DL) models, has revolutionized the potential for improving diagnosis, risk stratification, and personalized care across the ACHD spectrum. This narrative review discusses the current and future applications of AI in ACHD, including imaging interpretation, electrocardiographic analysis, risk stratification, procedural planning, and long-term care management. AI has been demonstrated as being highly accurate in congenital anomaly detection by various imaging modalities, automating measurement, and improving diagnostic consistency. Moreover, AI has been utilized in electrocardiography to detect previously undetected defects and estimate arrhythmia risk. Risk-prediction models based on clinical and imaging information can estimate stroke, heart failure, and sudden cardiac death as outcomes, thereby informing personalized therapy choices. AI also contributes to surgery and interventional planning through three-dimensional (3D) modelling and image fusion, while AI-powered remote monitoring tools enable the detection of early signals of clinical deterioration. While these insights are encouraging, limitations in data availability, algorithmic bias, a lack of prospective validation, and integration issues remain to be addressed. Ethical considerations of transparency, privacy, and responsibility should also be highlighted. Thus, future initiatives should prioritize data sharing, explainability, and clinician training to facilitate the secure and effective use of AI. The appropriate integration of AI can enhance decision-making, improve efficiency, and deliver individualized, high-quality care to ACHD patients.
成人先天性心脏病（ACHD）患者群体异质性强且不断扩大，在诊断和管理上面临独特挑战。传统检测方法无法有效反映病变的异质性和风险特征的变异性。包括机器学习（ML）和深度学习（DL）模型在内的人工智能（AI），彻底改变了改善ACHD全谱系诊断、风险分层和个性化治疗的可能性。本叙述性综述讨论了AI在ACHD中的当前及未来应用，包括影像解读、心电图分析、风险分层、手术规划和长期护理管理。通过各种成像模态，AI已被证明在先天性异常检测中具有高度准确性，可实现测量自动化并提高诊断一致性。此外，AI已应用于心电图检查，以检测先前未发现的缺陷并估计心律失常风险。基于临床和影像信息的风险预测模型可以将中风、心力衰竭和心源性猝死作为结果进行估计，从而为个性化治疗选择提供依据。AI还通过三维（3D）建模和图像融合为手术和介入规划做出贡献，而人工智能驱动的远程监测工具能够检测临床恶化的早期信号。尽管这些见解令人鼓舞，但数据可用性、算法偏差、缺乏前瞻性验证以及整合问题等局限性仍有待解决。还应强调透明度、隐私和责任等伦理考量。因此，未来的举措应优先考虑数据共享、可解释性和临床医生培训，以促进AI的安全有效使用。AI的适当整合可以增强决策制定、提高效率，并为ACHD患者提供个性化的高质量护理。
