Scholarlink

This bibliometric analysis examines 2,803 articles on artificial intelligence (AI) in electrocardiograms (ECG) for the detection of cardiovascular diseases (2014–2024). The United States and China lead the scientific production, with the Mayo Clinic and authors such as Friedman, Noseworthy and Attia standing out in the field. High-accuracy AI models includes Random Forest (100%), Active-DNN (99.86%) and 2D-CNN (99%). The most cited article (868 citations) underscores the role of convolutional neural networks (CNN) in atrial fibrillation detection. While AI optimizes cardiovascular diagnosis, further clinical validation across diverse population is needed.

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

Using Artificial Intelligence for the Detection of Heart Diseases by Electrocardiogram: A Bibliometric Analysis

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Fabio Misael Velasco Dorado,
  • Hugo Mitre-Hernandez,
  • Jezreel Mejía

摘要

This bibliometric analysis examines 2,803 articles on artificial intelligence (AI) in electrocardiograms (ECG) for the detection of cardiovascular diseases (2014–2024). The United States and China lead the scientific production, with the Mayo Clinic and authors such as Friedman, Noseworthy and Attia standing out in the field. High-accuracy AI models includes Random Forest (100%), Active-DNN (99.86%) and 2D-CNN (99%). The most cited article (868 citations) underscores the role of convolutional neural networks (CNN) in atrial fibrillation detection. While AI optimizes cardiovascular diagnosis, further clinical validation across diverse population is needed.