Scholarlink

<p>The application of artificial intelligence (AI) to congenital heart disease (CHD) has become a rapidly expanding field, promising to transform diagnostics, prognostics, and management. However, a comprehensive map of the global research landscape, its key contributors, thematic structure, and evolutionary trends is currently lacking. This study provides a bibliometric analysis to delineate this dynamic domain.&#xa0;We conducted a systematic search of the Web of Science Core Collection for all publications related to AI in CHD up to December 31, 2024. Bibliometric analyses were performed using VOSviewer and the Bibliometrix R package to map publication trends, international collaboration networks, leading contributors, and the conceptual structure of the field through co-occurrence and thematic mapping.&#xa0;Our analysis of 500 publications revealed an exponential growth in research output since 2020. The United States, China, and the United Kingdom were the most productive countries, forming central hubs in a robust international collaboration network. Harvard University and the University of London were the leading institutions. Thematic analysis identified six dominant research clusters: (1) AI-enhanced surgical/interventional support, (2) prenatal diagnosis via imaging, (3) disease-specific outcome modeling (e.g., Tetralogy of Fallot), (4) advanced imaging analytics with deep learning, (5) comprehensive risk and outcome management, and (6) pediatric cardiology applications. Temporal analysis confirmed a decisive recent shift towards deep learning methodologies, and analysis of highly cited works underscored the impact of AI in imaging and prognostic modeling.&#xa0;The convergence of AI and CHD has matured into a vibrant, clinically-focused research field with a clear technological trajectory towards deep learning. This global research panorama highlights established strengths in imaging and diagnostics while pointing to emerging frontiers in personalized medicine and interventional support. Fostering greater collaboration and focusing on clinical translation, model explainability, and equity will be crucial for realizing the full potential of this AI-driven transformation in improving care for patients with CHD.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A Paradigm Shift in Congenital Heart Disease: A Scientometric Portrait of the Rise of Computational Intelligence

  • 期刊论文

  • 发表日期：

    2025年11月21日

查看全文
  • Qingyong Zheng,
  • Molan Li,
  • Yongjia Zhou,
  • Jianguo Xu,
  • Ming Liu,
  • Yating Cui,
  • Junfei Wang,
  • Jinhui Tian

摘要

The application of artificial intelligence (AI) to congenital heart disease (CHD) has become a rapidly expanding field, promising to transform diagnostics, prognostics, and management. However, a comprehensive map of the global research landscape, its key contributors, thematic structure, and evolutionary trends is currently lacking. This study provides a bibliometric analysis to delineate this dynamic domain. We conducted a systematic search of the Web of Science Core Collection for all publications related to AI in CHD up to December 31, 2024. Bibliometric analyses were performed using VOSviewer and the Bibliometrix R package to map publication trends, international collaboration networks, leading contributors, and the conceptual structure of the field through co-occurrence and thematic mapping. Our analysis of 500 publications revealed an exponential growth in research output since 2020. The United States, China, and the United Kingdom were the most productive countries, forming central hubs in a robust international collaboration network. Harvard University and the University of London were the leading institutions. Thematic analysis identified six dominant research clusters: (1) AI-enhanced surgical/interventional support, (2) prenatal diagnosis via imaging, (3) disease-specific outcome modeling (e.g., Tetralogy of Fallot), (4) advanced imaging analytics with deep learning, (5) comprehensive risk and outcome management, and (6) pediatric cardiology applications. Temporal analysis confirmed a decisive recent shift towards deep learning methodologies, and analysis of highly cited works underscored the impact of AI in imaging and prognostic modeling. The convergence of AI and CHD has matured into a vibrant, clinically-focused research field with a clear technological trajectory towards deep learning. This global research panorama highlights established strengths in imaging and diagnostics while pointing to emerging frontiers in personalized medicine and interventional support. Fostering greater collaboration and focusing on clinical translation, model explainability, and equity will be crucial for realizing the full potential of this AI-driven transformation in improving care for patients with CHD.