Core Unit eHealth and Interoperability, BIH at Charité, Berlin, Germany.
Stud Health Technol Inform. 2024 Aug 22;316:820-821. doi: 10.3233/SHTI240537.
Congenital heart disease (CHD) represents a significant challenge in prenatal care due to low prenatal detection rates. Artificial Intelligence (AI) offers promising avenues for precise CHD prediction. In this study we conducted a systematic review according to the PRISMA guidelines, investigating the landscape of AI applications in prenatal CHD detection. Through searches on PubMed, Embase, and Web of Science, 621 articles were screened, yielding 28 relevant studies for analysis. Deep Learning (DL) emerged as the predominant AI approach. Data types were limited to ultrasound and MRI sequences mainly. This comprehensive analysis provides valuable insights for future research and clinical practice in CHD detection using AI applications.
先天性心脏病（CHD）是产前护理的重大挑战，因为其产前检出率较低。人工智能（AI）为精确预测 CHD 提供了有前景的途径。在本研究中，我们按照 PRISMA 指南进行了系统综述，调查了 AI 在产前 CHD 检测中的应用情况。通过在 PubMed、Embase 和 Web of Science 上进行检索，筛选出 621 篇文章，其中有 28 篇相关研究进行了分析。深度学习（DL）是 AI 方法的主要形式。数据类型主要限于超声和 MRI 序列。本全面分析为未来使用 AI 应用进行 CHD 检测的研究和临床实践提供了有价值的见解。
